Digital Twins Can Implement Both Streaming Analytics and Simulations

With the ScaleOut Digital Twin Streaming Service, the digital twin software model has proven its versatility well beyond its roots in product lifecycle management (PLM). This cloud-based service uses digital twins to implement streaming analytics and add important contextual information not possible with other stream-processing architectures. Because each digital twin can hold key information about an individual data source, it can enrich the analysis of incoming telemetry and extracts important, actionable insights without delay. Hosting digital twins on a scalable, in-memory computing platform enables the simultaneous tracking of thousands — or even millions — of data sources.

Owing to the digital twin’s object-oriented design, many diverse applications can take advantage of its powerful but easy-to-use software architecture. For example, telematics applications use digital twins to track telemetry from every vehicle in a fleet and immediately identify issues, such as lost or erratic drivers or emerging mechanical problems. Airlines can use digital twins to track the progress of passengers throughout an itinerary and respond to delays and cancellations with proactive remedies that smooth operations and reduce stress. Other applications abound, including health informatics, financial services, logistics, cybersecurity, IoT, smart cities, and crime prevention.

Here’s an example of a telematics application that tracks a large fleet of vehicles. Each vehicle has a corresponding digital twin analyzing telemetry from the vehicle in real time:

Applications like these need to simultaneously track the dynamic behavior of numerous data sources, such as IoT devices, to identify issues (or opportunities) as quickly as possible and give systems managers the best possible situational awareness. To either validate streaming analytics code for a complex physical system or model its behavior, it is useful to simulate the devices and the telemetry that they generate. The ScaleOut Digital Twin Streaming Service now enables digital twins to simplify both tasks.

Use Digital Twins to Simulate a Workload for Streaming Analytics

Digital twins can implement a workload generator that generates telemetry used in validating streaming analytics code. Each digital twin models the behavior of a physical data source, such as a vehicle in fleet, and the messages it sends and receives. When running in simulation, thousands of digital twins can then generate realistic telemetry for all data sources and feed streaming analytics, such as a telematics application, designed to track and analyze its behavior. In fact, the streaming service enables digital twins to implement both the workload generator and the streaming analytics. Once the analytics code has been validated in this manner, developers can then deploy it to track a live system.

Here’s an example of using a digital twin to simulate the operations of a pump and the telemetry (such as the pump’s temperature and RPM) that it generates. Running in simulation, this simulated pump sends telemetry messages to a corresponding real-time digital twin that analyzes the telemetry to predict impending issues:

Once the simulation has validated the analytics, the real-time digital twin can be deployed to analyze telemetry from an actual pump:

This example illustrates how digital twins can both simulate devices and provide streaming analytics for a live system.

Using digital twins to build a workload generator enables investigation of a wide range of scenarios that might be encountered in typical, real-world use. Developers can implement parameterizable, stateful models of physical data sources and then vary these parameters in simulation to evaluate the ability of streaming analytics to analyze and respond in various situations. For example, digital twins could simulate perimeter devices detecting security intrusions in a large infrastructure to help evaluate how well streaming analytics can identify and classify threats. In addition, the streaming service can capture and record live telemetry and later replay it in simulation.

Use Digital Twins to Simulate a Large System with Many Entities

In addition to using digital twins for analyzing telemetry, the ScaleOut Digital Twin Streaming Service enables digital twins to implement time-driven simulations that model large groups of interacting physical entities. Digital twins can model individual entities within a large system, such as airline passengers, aircraft, airport gates, and air traffic sectors in a comprehensive airline model. These digital twins maintain state information about the physical entities they represent, and they can run code at each time step in the simulation model’s execution to update digital twin state over time.  These digital twins also can exchange messages that model interactions.

For example, an airline tracking system can use simulation to model numerous types of weather delays and system outages (such as ground stops) to see how their system manages passenger needs. As the simulation model evolves over time, simulated aircraft can model flight delays and send messages to simulated passengers that react by updating their itineraries. Here is a depiction of an airline tracking simulation:

In contrast to the use of digital twins for PLM, which typically embody a complex design within a single digital twin model, the ScaleOut Digital Twin Streaming Service enables large numbers of physical entities and their interactions to be simulated. By doing this, simulations can model intricate behaviors that evolve over time and reveal important insights during system design and optimization. They also can be fed live data and run faster than real time as a tool for making predictions that assist decision-making by managers (such as airline dispatchers).

Scalable, In-Memory Computing Makes It Possible

Digital twins offer a compelling software architecture for implementing time-driven simulations with thousands of entities. In a typical implementation, developers create multiple digital twin models to describe the state information and simulation code representing various physical entities, such as trucks, cargo, and warehouses in a telematics simulation. They create instances of these digital twin models (simply called digital twins) to implement all of the entities being simulated, and the streaming service runs their code at each time step being simulated. During each time step, digital twins can exchange messages that represent simulated interactions between physical entities.

The ScaleOut Digital Twin Streaming Service uses scalable, in-memory computing technology to provide the speed and memory capacity needed to run large simulations with many entities. It stores digital twins in memory and automatically distributes them across a cluster of servers that hosts a simulation. At each time step, each server runs the simulation code for a subset of the digital twins and determines the next time step that the simulation needs to run. The streaming service orchestrates the simulation’s progress on the cluster and advances simulation time at a rate selected by the user.

In this manner, the streaming service can harness as many servers as it needs to host a large simulation and run it with maximum throughput. As illustrated below, the service’s in-memory computing platform can add new servers while a simulation is running, and it can transparently handle server outages should they occur. Users need only focus on building digital twin models and deploying them to the streaming service.

The Next Generation of Simulation with Digital Twins

Digital twins have historically been employed as a tool for simulating increasingly detailed behavior of a complex physical entity, like a jet engine. The ScaleOut Digital Twin Streaming Service takes digital twins in a new direction: simulation of large systems. Its highly scalable, in-memory computing architecture enables it to easily simulate many thousands of entities and their interactions. This provides a powerful new tool for extracting insights about complex systems that today’s managers must operate at peak efficiency. Its analytics and predictive capabilities promise to offer a high return on investment in many industries.

The post Simulate at Scale with Digital Twins appeared first on ScaleOut Software.

Using Digital Twins for Streaming Analytics

In the two years since we initially released the ScaleOut Digital Twin Streaming Service, we have applied the digital twin model to numerous use cases, including security alerting, telematics, contact tracing, logistics, device tracking, industrial sensor monitoring, cloned license plate detection, and airline system tracking. Constructing applications for these use cases has demonstrated the power of the digital twin model in creating streaming analytics that track large numbers of data sources.

The process of building digital twin applications allowed us to surface both the strengths and shortcomings of our APIs. This has led to a series of new features which enhance the core platform. For example, we created a rules engine for implementing the logic within a digital twin so that new models can be created without the need for programming expertise. We then added machine learning to digital twin models using Microsoft’s ML.NET library. This enables digital twins to look for patterns in telemetry that are difficult to define with code. More recently, we integrated our digital twin model with Microsoft’s Azure Digital Twins to accelerate real-time processing using our in-memory computing technology while providing new visualization and persistence capabilities for digital twins.

With the newly announced version 2, we are adding important new capabilities for real-time analytics to our digital twin APIs. Let’s take a look at some of these new features.

New Support for .NET 6

Version 2 expands the target platforms for C#-based digital twin models by supporting .NET 6. With our goal to make the ScaleOut Digital Twin Streaming Service’s feature set and visualization tools uniformly available in the cloud and on-premises, we recognized that we needed to move beyond support for .NET Framework, which can only be deployed on Windows. By adding .NET 6, we can take advantage of its portability across both Windows and Linux. Now C#, Java, JavaScript, and rules-based digital twin models can be deployed on all platforms:

(As illustrated with the dotted lines above, we continue to support .NET Framework on Windows and in the Azure cloud.)

To take maximum advantage of .NET 6, we also re-implemented our Azure cloud service and key portions of the back-end infrastructure in .NET 6. This provides better performance and flexibility for future upgrades.

Digital Twin Timers

Using our APIs, digital twins can run analytics code to process incoming messages from their corresponding data sources. In developing a proof-of-concept application for an industrial safety application, we learned that they also need to be able to create timers and run code when the timers expire. This enables digital twins to detect when their data sources fail or become erratic in sending messages.

For example, consider a digital application that tracks periodic telemetry from a collection of building thermostats. Each digital twin looks for abnormal temperature excursions that indicate the need to alert personnel. In addition, a digital twin must determine if its thermostat has failed and is no longer sending periodic temperature readings. By setting a timer and restarting it after each message is received, the digital twin can signal an alert if excessive time elapses between incoming messages:

In the actual industrial safety application we built, buildings throughout a site had numerous smoke and gas sensors. Digital twins for the sensors incorporated timers to detect failed sensors. As shown below, they periodically forwarded their status to a hierarchy of digital twins arranged as shown below from the lowest level upwards. The digital twins represented floors within buildings, buildings within a site, sites within the organization, and the overall organization itself. At each level, status information was aggregated to gives personnel immediate information about where problems were occurring. The role of timers was critical in maintaining a complete picture of the organization’s status.

Aggregate Initialization

When we first implemented our digital twin platform, we designed it to automatically create a digital twin instance when the first message from an unknown data source arrives. (The platform determines which type of digital twin to create from the message’s contents.) This technique simplifies deployment by avoiding the need to explicitly create digital twin instances. The user simply develops and deploys a digital twin model, for example, for a gas sensor, and the platform creates a digital twin for each sensor that sends a message to the platform.

In many cases, it’s useful to create digital twin instances when deploying a model instead of waiting for messages to arrive. For example, both demo applications and simulations need to explicitly create digital twins since there are no actual physical devices. Also, applications with model hierarchies (like the example above) may need to create instances to fill out the hierarchy and start reporting at deployment time.

To address these needs, version 2 lets users supply a csv file when deploying a digital twin model. This csv file lists all digital twin instances and the initial values for each instance’s properties. The platform then creates the corresponding digital twin instances and sets the initial values.

Here’s an example that shows how a csv file generated from a spreadsheet can be deployed to the streaming service via the UI to initialize five digital twin instances. Note that the spreadsheet’s first row has the names of the properties to be set:

Summing Up

After more than two years of experience in building real-world applications with digital twins, we have confirmed the power of using digital twins for streaming analytics. Because digital twins bring together state information, telemetry, and application logic for each physical device, they enable deep introspection that tracks behavior and surfaces issues using a simple, highly efficient programming model. They also allow applications to focus on analytics code and defer the challenges of data visualization and throughput scaling to the streaming service.

With version 2, we have added important new capabilities to our implementation of the digital twin model and to the underlying platform. These features have been driven by emerging requirements that surfaced during application development. This matches our design philosophy of starting with a simple, coherent model and carefully enhancing it as new learnings are made.

Interestingly, our development work has consistently shown the value of using simulation to demonstrate the capabilities of the digital twin model for streaming analytics. The new features in version 2 enhance our ability to build simulations, and we expect to add more support for simulation in upcoming releases. Stay tuned.

The post New Digital Twin Features for Real-World Applications appeared first on ScaleOut Software.

ScaleOut Software is excited to announce the release of ScaleOut In-Memory Database, which offers a new, highly scalable, clustered server platform for running Redis commands. This platform uses ScaleOut’s patented, quorum-based clustering technology to replace open-source Redis’s cluster implementation. It fully automates Redis cluster management while preserving the use of open-source Redis code to process commands. In doing so, ScaleOut In-Memory Database lets enterprise Redis users manage server clusters with much greater ease and lower both their acquisition and management costs (TCO) — while preserving a native execution environment for Redis applications. ScaleOut In-Memory Database runs on both Linux and Windows systems. 

What sets ScaleOut’s cluster architecture apart

When ScaleOut Software first developed its clustering technology for scalable in-memory data storage in 2003, we had to tackle several technical challenges. We needed to:  

• implement a scalable cluster membership,
• partition the in-memory data store across multiple servers,
• replicate updates with zero data loss (i.e., avoid eventual consistency), and
• maximize throughput with multi-threading on multicore servers.

We also realized that it was important not to expose all these complexities to users. The cluster had to be easy to manage, making a simple learning curve for system administrators. It was also vital to have a straightforward view of the data store for applications (that is, maintain location transparency and full consistency) so developers could target it easily. 

Automated clustering 

Our clustering architecture has many leading-edge automated clustering features. These include the ability to:  

• self-organize multiple servers into a cluster,
• automatically partition data and distribute it across the cluster,
• load-balance stored data as servers are added or removed,
• automatically create and maintain replicas,
• detect server and network failures,
• recover from failures by promoting replicas to replace failed primary partitions, and
• “self-heal” by creating new replicas to replace lost ones.

Stability and consistency 

The server cluster uses peer-to-peer algorithms to avoid single points of failure. Running on one or more servers, it maintains availability to applications even if all but one server fails. It uses a patented quorum algorithm to implement full (strong) consistency when updating stored data across multiple servers. Lastly, it executes multiple requests at once using a multi-threaded architecture. 

Industry-leading ease of use 

ScaleOut’s cluster architecture does all this without showing its inner workings to developers or system administrators. Developers see a single, reliable data store that happens to be distributed across multiple servers. System administrators see a set of servers on a single network subnet, each running a single service process.  

Once the service is configured to select a specific subnet (if multiple NICs are in use), it joins the cluster with one click and is ready to take on its share of the workload. Building a server cluster is just a matter of adding servers (called “nodes” in Redis documentation): 

All this automation minimizes the workload for system administrators, lowering costs and increasing uptime. Administrators are unaware of the cluster’s data partitioning mechanism and replica placement. They don’t need to intervene to recover and heal the data store if a server fails or becomes isolated. They also don’t need to spin up multiple service processes per node to extract more throughput from multicore servers.

Enter Redis

Open-source Redis was first created in 2009 for use on a single server, with clustering added in 2015. It has gained widespread popularity because of its rich set of data structures and commands. At the enterprise level, it has seen fast-growing adoption across many applications. As a result, the need to streamline cluster management procedures and increase data reliability for Redis users has become more urgent. 

Introducing automated Redis clustering with ScaleOut In-Memory Database 

We created ScaleOut In-Memory Database to meet this need. This product integrates open-source Redis code (version 6.2.5) that implements all the popular Redis data structures (strings, lists, sets, hashes, streams, and more) into ScaleOut’s automated cluster architecture and execution platform. Now, system administrators don’t need to manage Redis concepts like hashslots and shards. Instead, ScaleOut takes over these tasks using its built-in, fully automated mechanisms. Automated recovery and self-healing eliminate the need for manual intervention and increase uptime. What’s more, ScaleOut’s quorum-based updates replace Redis’s eventual consistency mechanism to deliver reliable data storage across servers. Applications can depend on the server cluster to survive a server failure without data loss, and the cluster remains available even if multiple servers fail. 

To boost throughput and automatically make full use of all available processing cores, ScaleOut In-Memory Database integrates Redis command execution with its multi-threaded processing of client requests. Achieving this meant eliminating Redis’s native, single-threaded event-loop execution model without introducing a global lock that would constrain performance. The result is that each server in the cluster can run Redis commands simultaneously on all processing cores using a single service process. 

Power with simplicity

We designed ScaleOut’s peer-to-peer cluster architecture to serve as the foundation for all user services. Hence, functions like clearing the database and backup/restore were built from the outset to run in parallel across all servers. This approach reduces the system administrator’s workload and delivers fast performance. To give Redis users the benefit of a fully parallel architecture, ScaleOut In-Memory Database provides a cluster-wide implementation of many Redis commands, such as PUBLISH and FLUSHALL. 

ScaleOut In-Memory Database also overcomes the single-server limitation of the Redis SAVE command. It provides a cluster-wide implementation of backup/restore using its built-in parallel backup/restore utility. This allows system administrators to backup all Redis objects with one click in ScaleOut’s management console, and it delivers parallel speedup by running simultaneously on all servers. The user can backup either to local disks: 

or to a single, shared disk:

System administrators can cut down their workload by restoring backup files to a different cluster configuration than they used to make the backup. For example, it’s possible to restore a backup from a three-server cluster to a two-server cluster with a different hashslot mapping: 

There’s a lot more in the new ScaleOut In-Memory Database than there’s room to discuss in depth here. For example, ScaleOut’s cluster stalls Redis command execution automatically when it moves hashslots between nodes for load-balancing, or when it performs recovery. This means clients always have a consistent view of the cluster. Also, the cluster stores Redis objects in their own ScaleOut namespace side-by-side with objects that ScaleOut’s native APIs manage. This lets users access the full power of ScaleOut’s in-memory computing features, including cluster-wide, data-parallel operations and stream processing with digital twins. 

Summing Up

ScaleOut In-Memory Database makes scalable processing more convenient, reliable, and cost-effective for enterprise Redis users than ever before. By automating Redis cluster management, improving data reliability, and adding multi-threaded command execution, this product can significantly drive down the total cost of ownership for Redis deployments, even in comparison to commercial Redis alternatives. We invite you to check it out and see how it performs for you. We’d love to hear your feedback. 

*Redis is a registered trademark of Redis Ltd. and the Redis box logo is a mark of Redis Ltd. Any rights therein are reserved to Redis Ltd. Any use by ScaleOut Software is for referential purposes only and does not indicate any sponsorship, endorsement or affiliation between Redis and ScaleOut Software.

The post Announcing ScaleOut In-Memory Database: Automated Clustering for Redis Users appeared first on ScaleOut Software.

The Challenge

Redis^®* offers a compelling set of data structures that enhance the capabilities of a distributed cache beyond just storing serialized objects. Created in 2009 as a single-server store to assist in the design of a web server, Redis gives applications numerous useful options for organizing stored data, including sets, lists, and hashes. Cluster support was added later, and it introduced specialized concepts, like hashslots and master/replica shards, that system administrators must understand and manage. Along with its use of eventual consistency, this has created complexity that makes cluster management challenging while reducing flexibility in configurations.

In contrast, ScaleOut StateServer®, a distributed cache for serialized objects and first released in 2005, was designed from the ground up to run on a server cluster with automated load-balancing, data replication, and recovery while storing data with full consistency (i.e., sequential consistency) across replicas. It also executes client requests using all available processing cores for maximum throughput. These features dramatically simplify cluster management, especially for enterprise users, improve flexibility, and lower TCO. For example, unlike Redis, ScaleOut server clusters can seamlessly grow from a single to multiple servers, and system administrators do not need to manage hashslots or master/replica shards. See a recent blog post that discusses how ScaleOut StateServer simplifies cluster management in comparison to Redis.

ScaleOut Software recognized that running Redis commands on a ScaleOut StateServer cluster would offer Redis users the best of both worlds: familiar and rich data structures combined with significantly simpler cluster management and full data consistency. However, the ideal implementation would need to use Redis open-source code to execute Redis commands so that client commands would behave identically to open-source Redis clusters. The challenge is then to integrate Redis code into ScaleOut StateServer’s execution platform and take advantage of ScaleOut’s highly automated clustering features while eliminating the single-threaded constraints of Redis’s event-loop architecture.

Integrating Redis into ScaleOut StateServer

Released as a community preview, version 5.11 of ScaleOut StateServer introduces support for the most popular Redis data structures (strings, sets, lists, hashes, and sorted sets) plus publish/subscribe commands, transactions, and various utility commands (such as FLUSHDB and EXPIRE). Both Windows and Linux versions are available. This release uses open-source Redis version 6.2.5 to process Redis commands.

Redis clients connect to any ScaleOut StateServer server in a cluster using the standard RESP protocol. (A cluster can contain one or more servers.) Client libraries internally obtain the mapping of hashslots to servers using either the CLUSTER SLOTS or CLUSTER NODES commands and then direct Redis access requests to the appropriate ScaleOut server. To maximize throughput, each ScaleOut server processes incoming Redis commands on multiple threads using all available processor cores; there is no need to deploy multiple shards on each server for this purpose.

The following diagram shows a set of Redis clients connecting to a ScaleOut StateServer cluster. Note that the complexities of hashslots and shards have been eliminated:

As the need for additional throughput grows, system administrators can simply join new servers to the cluster. ScaleOut StateServer automatically rebalances the hashslots across the cluster as servers are added or removed. It also delays execution of Redis commands during load-balancing (and recovery) to give clients a consistent picture of hashslot placement and avoid client exceptions. After a hashslot has fully migrated to a remote server, a requesting client is returned the Redis -MOVED indication so that it can redirect its request to the new server.

The following diagram illustrates how ScaleOut StateServer automatically manages hashslots. In this example, it migrates half of the hashslots to a second server that joins a cluster:

ScaleOut StateServer automatically creates replicas for all hashslots. There is no need for system administrators to manually create master and replica shards or move them from server to server during membership changes and recovery. ScaleOut StateServer automatically places replicas on different servers from their corresponding primary hashslots and migrates them as necessary during membership changes to ensure optimal load-balancing. If a server fails or has a network outage, ScaleOut StateServer automatically “self-heals” by promoting replicas to primaries and creating new replicas as necessary.

To avoid serving stale data to clients after recovery from an outage, ScaleOut StateServer uses a patented quorum algorithm to implement fully consistent updates to stored objects. In contrast, Redis uses an eventual consistency model for updating replicas. (To maximize throughput at the expense of data consistency, ScaleOut StateServer can optionally be configured for eventual consistency.) When a server receives a Redis command, it executes this command on a quorum containing the primary hashslot and replicas (one or two in the current implementation) prior to returning to the client. Transactions are processed in the same manner.

The following diagram compares the full and eventually consistent models for updating replicas and shows how they differ in behavior. A fully consistent update waits for the replica to be updated prior to returning to the client, whereas an eventually consistent update does not. If a primary server should fail prior to committing the replica’s update, the cluster could lose the update and serve stale data to clients.

Implementation Details

The following diagram shows how Redis open-source code has been integrated into ScaleOut StateServer:

Redis open-source code (shown in the red box) implements command parsing and processing, the data structure commands, transactions, publish/subscribe commands, and blocking commands. ScaleOut StateServer takes over all clustering functions, including request processing, membership, quorum processing of updates, load-balancing, recovery, and self-healing. It also uses a proprietary transport protocol for server-to-server communication.

As illustrated below, ScaleOut StateServer uses multi-threaded execution for Redis commands to take advantage of all processing cores and eliminate the need for multiple primary shards on each server. In contrast, Redis executes commands using an event loop that processes commands sequentially on a single processing core:

To accomplish this, ScaleOut StateServer has implemented a command scheduler that independently executes commands for each hashslot so that they can run in parallel without global locking.

What’s Missing?

The community preview release focuses on demonstrating support for Redis data structures, which represent the widely used core of Redis functionality. It does not include support for Redis streams, Lua scripting, modules, AOL/RDB persistence, ACLs, and Redis configuration files. In addition, many utility commands which are not required, such as cluster commands for manually moving hashslots, are not supported. Lastly, this version does not incorporate all of the performance enhancements in development for the production release.

Summing Up

ScaleOut’s new integration of Redis open-source code into ScaleOut StateServer was designed to bring powerful new capabilities to Redis users while ensuring native-Redis behavior for client applications. Targeted to meet the needs of enterprise users, it dramatically simplifies the management of Redis clusters by automating all cluster operations, and it ensures that fully consistent updates are performed by Redis commands. In addition, this integration runs alongside ScaleOut StateServer’s native APIs, which incorporate advanced features not available on open-source Redis clusters, such as data-parallel computing, streaming analytics, and coherent, wide-area data replication.

ScaleOut Software is excited to hear your feedback about the community preview and learn what additional features you would like to see in the upcoming production release. You can download ScaleOut StateServer, which incorporates the preview release, here for Linux or Windows and try it out now. Let us know what you think.

*Redis is a registered trademark of Redis Ltd. and the Redis box logo is a mark of Redis Ltd. Any rights therein are reserved to Redis Ltd. Any use by ScaleOut Software is for referential purposes only and does not indicate any sponsorship, endorsement or affiliation between Redis and ScaleOut Software.

The post Introducing A New Execution Platform for Redis Clients appeared first on ScaleOut Software.

When tracking telemetry from a large number of IoT devices, it’s essential to quickly detect when something goes wrong. For example, a fleet of long-haul trucks needs to meet demanding schedules and can’t afford unexpected breakdowns as a fleet manager manages  thousands of trucks on the road. With today’s IoT technology, these trucks can report their engine and cargo status every few seconds to cloud-hosted telematics software. How can this software sift through the flood of incoming messages to identify emerging issues and avoid costly failures? Can the power of machine learning be harnessed to provide predictive analytics that automates the task of finding problems that are otherwise very difficult to detect?

As described in earlier blog posts, real-time digital twins offer a powerful software architecture for tracking and analyzing IoT telemetry from large numbers of data sources. A real-time digital twin is a software component running within a fast, scalable in-memory computing platform, and it hosts analytics code and state information required to track a single data source, like a truck within a fleet. Thousands of real-time digital twins run together to track all of the data sources and enable highly granular real-time analysis of incoming telemetry. By building on the widely used digital twin concept, real-time digital twins simultaneously enhance real-time streaming analytics and simplify application design.

Incorporating machine learning techniques into real-time digital twins takes their power and simplicity to the next level. While analytics code can be written in popular programming languages, such as Java and C#, or even using a simplified rules engine, creating algorithms that ferret out emerging issues hidden within a stream of telemetry still can be challenging. In many cases, the algorithm itself may be unknown because the underlying processes which lead to device failures are not well understood. In these cases, a machine learning (ML) algorithm can be trained to recognize abnormal telemetry patterns by feeding it thousands of historic telemetry messages that have been classified as normal or abnormal. No manual analytics coding is required. After training and testing, the ML algorithm can then be put to work monitoring incoming telemetry and alerting when it observes suspected abnormal telemetry.

To enable ML algorithms to run within real-time digital twins, ScaleOut Software has integrated Microsoft’s popular machine learning library called ML.NET into its Azure-based ScaleOut Digital Twin Streaming Service. Using the ScaleOut Model Development Tool (formerly called the ScaleOut Rules Engine Development Tool), users can select, train, evaluate, deploy, and test ML algorithms within their real-time digital twin models. Once deployed, the ML algorithm runs independently for each data source, examining incoming telemetry within milliseconds after it arrives and logging abnormal events. The real-time digital twin also can be configured to generate alerts and send them to popular alerting providers, such as Splunk, Slack, and Pager Duty. In addition, business rules optionally can be used to further extend real-time analytics.

The following diagram illustrates the use of an ML algorithm to track engine and cargo parameters being monitored by a real-time digital twin hosting an ML algorithm for each truck in a fleet. When abnormal parameters are detected by the ML algorithm (as illustrated by the spike in the telemetry), the real-time digital twin records the incident and sends a message to the alerting provider:

Training an ML algorithm to recognize abnormal telemetry just requires supplying a training set of historic data that has been classified as normal or abnormal. Using this training data, the ScaleOut Model Development Tool lets the user train and evaluate up to ten binary classification algorithms supplied by ML.NET using a technique called supervised learning. The user can then select the appropriate trained algorithm to deploy based on metrics for each algorithm generated during training and testing. (The algorithms are tested using a portion of the data supplied for training.)

For example, consider an electric motor which periodically supplies three parameters (temperature, RPM, and voltage) to its real-time digital twin for monitoring by an ML algorithm to detect anomalies and generate alerts when they occur:

Training the real-time digital twin’s ML model follows the workflow illustrated below:

Here’s a screenshot of the ScaleOut Model Development Tool that shows the training of selected ML.NET algorithms for evaluation by the user:

The output of this process is a real-time digital twin model which can be deployed to the streaming service. As each motor reports its telemetry to the streaming service, a unique real-time digital twin “instance” (a software object) is created to track that motor’s telemetry using the ML algorithm.

In addition to supervised learning, ML.NET provides an algorithm (called an adaptive kernel density estimation algorithm) for spike detection, which detects rapid changes in telemetry for a single parameter. The ScaleOut Model Development Tool lets users add spike detection for selected parameters using this algorithm. In addition, it is often useful to detect unusual but subtle changes in a parameter’s telemetry over time. For example, if the temperature for an electric motor is expected to remain constant, it would be useful to detect a slow rise in temperature that might otherwise go unobserved. To address this need, the tool lets users make use of a ScaleOut-developed, linear regression algorithm that detects and reports inflection points in the telemetry for a single parameter. These two techniques for tracking changes in a telemetry parameter are illustrated below:

Summing Up

Machine learning provides important real-time insights that enhance situational awareness and enable fast, effective responses. They often can provide useful analytics for complex datasets that cannot be analyzed with hand-coded algorithms. Their usefulness and rate of adoption is quickly growing. Using the ScaleOut Model Development Tool, real-time digital twins now can easily be enhanced to automatically analyze incoming telemetry messages with machine learning techniques that take full advantage of Microsoft’s ML.NET library. The integration of machine learning with real-time digital twins enables thousands of data streams to be automatically and independently analyzed in real-time with fast, scalable performance. Best of all, no coding is required, enabling fast, easy model development. By combining ML with real-time digital twins, the ScaleOut Digital Twin Streaming Service adds important new capabilities for real-time streaming analytics that supercharge the Azure IoT ecosystem.

Read more about the ScaleOut Model Development Tool.

The post Machine Learning Supercharges Real-Time Digital Twins appeared first on ScaleOut Software.

ScaleOut’s Battle-Tested Clustering Technology Give It Key Advantages Over Redis®* in Ease of Use and Performance

By William L. Bain and Bryce C. Klinker

Breaking news: ScaleOut Software has announced a community preview of support for Redis clients in ScaleOut StateServer. Learn more here.

Distributed caching technology first hit the market in about 2001 with the introduction of Tangosol Coherence and has been evolving ever since. Designed to help applications scale performance by eliminating bottlenecks in accessing data, this distributed computing technology stores live, fast-changing data in memory across a cluster of inexpensive, commodity servers or virtual machines. The combination of fast, memory-based data storage and throughput scaling with multiple servers results in consistently fast access and update times for growing workloads, such as e-commerce, financial services, IoT device tracking, and other applications.

ScaleOut Software introduced its distributed caching product, ScaleOut StateServer® (SOSS), in 2005 and has made continuous enhancements over the last 16 years. While the single-server version of Redis was released in 2009 by Salvatore Sanfilippo, clustering support was first added in 2015. These two products embody highly different design goals. SOSS was designed as an integrated distributed caching architecture incorporating transparent throughput scaling and high availability using data replication with the goals of maximizing performance, ease of use, and portability across operating systems. In contrast, according to M. Russo, Redis was conceived as a single-server, data-structure store to improve the performance of a real-time data analytics product. (Beyond just storing strings or opaque objects, a data-structure store also implements various data types, such as lists and sorted sets.) Clustering was added to Redis’ single-server architecture after 4 years to provide a way to scale.

As background for the following discussion, it’s important to review some key concepts. Most distributed caches use a key/value storage model that identifies stored objects using string keys. To distribute objects across multiple servers in a cluster, a distributed cache typically maps keys to hash slots, each of which holds a subset of objects. The cache then distributes hash slots across the servers and moves them between servers as needed to balance the workload; this process is called sharding. A group of hash slots running on a single server (called a node here) can either be a primary or replica. Clients direct updates to the target hash slot on a primary node, which replicates the update to one or more replica nodes for high availability in case the primary node fails.

Ease of Use

The differences in design goals of the two technologies have led to very different impacts on users. To maximize ease of use, SOSS automatically creates and manages hash slots for the user, including primaries and replicas. Using a built-in load-balancer, each service internally manages a subset of both primary and replica hash slots, as illustrated below. Users just create a single SOSS service process on every node, and these service processes discover each other and distribute the hash slots among themselves to balance the workload. They also automatically handle all aspects of recovery after a node fails.

In contrast, Redis users create separate service processes on each node for primary and replica hash slots and must manually distribute the hash slots among the primaries. (Unlike SOSS, a 1-node or 2-node Redis cluster is not allowed.) As we will see below, users must perform a complex set of manual actions when adding and removing nodes and to heal and rebalance the cluster after a node fails. The following diagram illustrates the difference between Redis and SOSS in the user’s view of the cluster:

Adding a Node to the Cluster Using SOSS

To illustrate how SOSS’s built-in mechanisms for managing hash slots, load-balancing, failure detection, and self-healing simplify cluster management, let’s look at the steps needed to add a node to the cluster. When using SOSS, the user just installs the service on a new node and clicks a button in the management console to join the cluster. Using multicast discovery (or optional host list if multicast is not available), the service process automatically receives primary and replica hash slots and starts handling its portion of the workload. The following diagram shows the addition of a fourth node to a cluster:

Adding a Node to the Cluster Using Redis

Because Redis requires the user to manage the creation of primary and replica service processes (sometimes called shards) and the management of hash slots, many more steps must be performed to add a node to the cluster. To accomplish this, the user runs administrative commands that create the new processes, connect the primaries and replicas, move the replicas as necessary, and reallocate the hash slots among the nodes. The required configuration changes are illustrated below:

Here is an example of administrative steps required to make the configuration changes (using node 0’s IP and port as the bootstrap address for the new node):

// Start up a new replica redis-server instance on node 3 for primary 2:
redis-cli --cluster add-node host3Ip:replicaPort node0Ip:node0Port --cluster-slave 
          --cluster-master-id primary2NodeID
// Start up a new primary redis-server instance on node 3:
redis-cli --cluster add-node host3Ip:primaryPort existingIp:existingPort 
// Connect to replica 2 on node 0 and modify it to replicate primary 3: 
redis-cli -h replica2Ip -p -replica2Port > cluster replicate primary3NodeID
// Reshard the cluster by interactively moving hash slots from existing nodes to node 3:
redis-cli --cluster reshard existingIp:existingPort
> How many slots to move? 4096 //16384 / 4 = 4096
> What node to move slots to? primary3NodeID // (primary3NodeID returned by previous command)
> What nodes to move slots from? all

This process is complex, and it becomes more difficult to keep track of the distribution of hash slots with larger cluster memberships. Removing a node has comparable complexity.

Recovering After a Node Fails (SOSS and Redis)

SOSS’s service processes automatically detect and recover from the loss of a node. They use built-in, scalable, peer-to-peer heart-beating to detect missing node(s) and create a new, coherent cluster membership. Next, they promote replica hash slots to primaries on the surviving nodes, create new replicas for self-healing, and rebalance the workload across the nodes.

Redis does not implement a coherent cluster membership and does not provide automatic self-healing and recovery. Each Redis node sends heartbeat messages to random other nodes to detect possible failures, and the cluster uses a gossip mechanism to declare that a node has failed. After that, its replica on a different node promotes itself to a primary so that the hash slots remain available, but Redis does not self-heal by creating a new replica for the hash slots. Also, it does not automatically redistribute the hash slots across the nodes to rebalance the workload. These tasks are left to the system administrator, who needs to sort out the needed configuration changes and implement them to restore a fully redundant, balanced cluster.

Performance Comparison

The different design choices between SOSS and Redis also lead to semantic and performance differences. To maximize ease of use for application developers, SOSS maintains all stored data with full consistency (to be more precise, sequential consistency), ensuring that it only serves the latest updates and never loses data after the failure of a single server (or two servers if multiple replicas are used). This design choice targets enterprise applications that need to ensure that the distributed cache always returns the correct data. To implement data replication across multiple replicas with the highest possible performance, SOSS uses a patented quorum algorithm.

In contrast, Redis employs an eventual consistency model with asynchronous replication. In general, this choice enables higher throughput because updates do not have to wait for replication to complete before responding to the user. It also enables potentially higher read throughput by serving reads from replicas even if they are not guaranteed to serve the latest updates.

Given these two design choices, it’s valuable to compare the throughput of the two distributed caches as nodes are added and the workload is simultaneously increased, as illustrated below. This technique evaluates how well the caches can scale their throughput by adding nodes to handle increasing workload; linear throughput scaling ensures consistently fast response times. (For a discussion of throughput scaling in distributed systems, see Gustafson’s Law.).

To perform an apples-to-apples throughput comparison of Redis 6.2 and SOSS 5.10, SOSS was configured to use eventual consistency (“EC”) when updating replicas. The performance of SOSS with full consistency (“FC”) was also measured. Tests were run for 3, 4, and 6 node clusters in AWS on m5.xlarge instances with 4 cores@2.5 Ghz, and 16GB RAM. The clients ran read/update pairs on 100K objects of sizes 2KB and 20KB to represent a typical web workload with a 1:1 read/update ratio. The results are as follows:

SOSS provided consistently higher throughput than Redis when eventual consistency was used to perform updates (the blue and gray lines in the charts). Running SOSS with full consistency (the red lines) resulted in lower throughput, as expected, since updates have to be committed at the replica before responding to the client instead of being performed asynchronously. However, both Redis and SOSS with full consistency delivered close to the same throughput for 20KB objects. This may be due to benefits of SOSS’s client-side caching, which eliminated unnecessary data transfers during reads.

Summing Up

Our comparison of SOSS and Redis shows the benefits of ScaleOut’s integrated clustering architecture. A key design goal for SOSS was to simplify the user’s workload by providing a unified, location-transparent data cache with built-in, fully automatic load-balancing and high availability. By hiding the inner workings of hash slots, heart-beating, replica placement, load-balancing, and self-healing, the application developer and systems administrator can focus on simply using the distributed cache instead of configuring its implementation. In our view, Redis’s approach of exposing these complex mechanisms to the user significantly steepens the learning curve and increases the user’s workload.

It might come as a surprise to learn that in the above benchmark testing, SOSS maintained a consistent performance advantage. We attribute this to ScaleOut’s approach of designing an integrated cluster architecture from the outset instead of adding clustering to a single server data store, as Redis did. This approach enabled design freedom at every step to eliminate distributed bottlenecks, and it led to extensive use of multithreading and internal data sharding within each service process to extract maximum performance from multi-core servers.

Lastly, SOSS demonstrates that the CAP theorem doesn’t really prevent the use of full consistency when building a scalable, distributed cache. For many enterprise applications, which demand data integrity at all times, this may be the better choice.

Learn more about how ScaleOut StateServer compares to Redis.

*Redis is a registered trademark of Redis Ltd. and the Redis box logo is a mark of Redis Ltd. Any rights therein are reserved to Redis Ltd. Any use by ScaleOut Software is for referential purposes only and does not indicate any sponsorship, endorsement or affiliation between Redis and ScaleOut Software.

The post Redis vs ScaleOut: What You Need to Know appeared first on ScaleOut Software.

Real-Time Device Tracking with In-Memory Computing Can Fill an Important Gap in Today’s Streaming Analytics Platforms

We are increasingly surrounded by intelligent IoT devices, which have become an essential part of our lives and an integral component of business and industrial infrastructures. Smart watches report biometrics like blood pressure and heartrate; sensor hubs on long-haul trucks and delivery vehicles report telemetry about location, engine and cargo health, and driver behavior; sensors in smart cities report traffic flow and unusual sounds; card-key access devices in companies track entries and exits within businesses and factories; cyber agents probe for unusual behavior in large network infrastructures. The list goes on.

The Limitations of Today’s Streaming Analytics

How are we managing the torrent of telemetry that flows into analytics systems from these devices? Today’s streaming analytics architectures are not equipped to make sense of this rapidly changing information and react to it as it arrives. The best they can usually do in real-time using general purpose tools is to filter and look for patterns of interest. The heavy lifting is deferred to the back office. The following diagram illustrates a typical workflow. Incoming data is saved into data storage (historian database or log store) for query by operational managers who must attempt to find the highest priority issues that require their attention. This data is also periodically uploaded to a data lake for offline batch analysis that calculates key statistics and looks for big trends that can help optimize operations.

What’s missing in this picture? This architecture does not apply computing resources to track the myriad data sources sending telemetry and continuously look for issues and opportunities that need immediate responses. For example, if a health tracking device indicates that a specific person with known health condition and medications is likely to have an impending medical issue, this person needs to be alerted within seconds. If temperature-sensitive cargo in a long haul truck is about to be impacted by an erratic refrigeration system with known erratic behavior and repair history, the driver needs to be informed immediately. If a cyber network agent has observed an unusual pattern of failed login attempts, it needs to alert downstream network nodes (servers and routers) to block the kill chain in a potential attack.

A New Approach: Real-Time Device Tracking

To address these challenges and countless others like them, we need autonomous, deep introspection on incoming data as it arrives and immediate responses. The technology that can do this is called in-memory computing. What makes in-memory computing unique and powerful is its two-fold ability to host fast-changing data in memory and run analytics code within a few milliseconds after new data arrives. It can do this simultaneously for millions of devices. Unlike manual or automatic log queries, in-memory computing can continuously run analytics code on all incoming data and instantly find issues. And it can maintain contextual information about every data source (like the medical history of a device wearer or the maintenance history of a refrigeration system) and keep it immediately at hand to enhance the analysis. While offline, big data analytics can provide deep introspection, they produce answers in minutes or hours instead of milliseconds, so they can’t match the timeliness of in-memory computing on live data.

The following diagram illustrates the addition of real-time device tracking with in-memory computing to a conventional analytics system.  Note that it runs alongside existing components. It adds the ability to continuously examine incoming telemetry and generate both feedback to the data sources (usually, devices) and alerts for personnel in milliseconds:

In-Memory Computing with Real-Time Digital Twins

Let’s take a closer look at today’s conventional streaming analytics architectures, which can be hosted in the cloud or on-premises. As shown in the following diagram, a typical analytics system receives messages from a message hub, such as Kafka, which buffers incoming messages from the data sources until they can be processed. Most analytics systems have event dashboards and perform rudimentary real-time processing, which may include filtering an aggregated incoming message stream and extracting patterns of interest. These real-time components then deliver messages to data storage, which can include a historian database for logging and query and a data lake for offline, batch processing using big data tools such as Spark:

Conventional streaming analytics systems run either manual queries or automated, log-based queries to identify actionable events. Since big data analyses can take minutes or hours to run, they are typically used to look for big trends, like the fuel efficiency and on-time delivery rate of a trucking fleet, instead of emerging issues that need immediate attention. These limitations create an opportunity for real-time device tracking to fill the gap.

As shown in the following diagram, an in-memory computing system performing real-time device tracking can run alongside the other components of a conventional streaming analytics solution and provide autonomous introspection of the data streams from each device. Hosted on a cluster of physical or virtual servers, it maintains memory-based state information about the history and dynamically evolving state of every data source. As messages flow in, the in-memory compute cluster examines and analyzes them separately for each data source using application-defined analytics code. This code makes use of the device’s state information to help identify emerging issues and trigger alerts or feedback to the device. In-memory computing has the speed and scalability needed to generate responses within milliseconds, and it can evaluate and report aggregate trends every few seconds.

Because in-memory computing can store contextual data and process messages separately for each data source, it can organize application code using a software-based digital twin for each device, as illustrated in the diagram above. Instead of using the digital twin concept to model the inner workings of the device, a real-time digital twin tracks the device’s evolving state coupled with its parameters and history to detect and predict issues needing immediate attention. This provides an object-oriented mechanism that simplifies the construction of real-time application code that needs to evaluate incoming messages in the context of the device’s dynamic state. For example, it enables a medical application to determine the importance of a change in heart rate for a device wearer based on the individual’s current activity, age, medications, and medical history.

Summing Up

The complex web of communicating devices that surrounds us needs intelligent, real-time device tracking to extract its full benefits. Conventional streaming analytics architectures have not kept up with the growing demands of IoT. With its combination of fast data storage, low-latency processing and ease of use, in-memory computing can fill the gap while complementing the benefits provided by historian databases and data lakes. It can add the immediate feedback that IoT applications need and boost situational awareness to a new level, finally enabling IoT to deliver on its promises.

The post The Need for Real-Time Device Tracking appeared first on ScaleOut Software.

The population of intelligent IoT devices is exploding, and they are generating more telemetry than ever. Whether it’s health-tracking watches, long-haul trucks, or security sensors, extracting value from these devices requires streaming analytics that can quickly make sense of the telemetry and intelligently react to handle an emerging issue or capture a new opportunity.

The Microsoft Azure IoT ecosystem offers a rich set of capabilities for processing IoT telemetry, from its arrival in the cloud through its storage in databases and data lakes. Acting as a switchboard for incoming and outgoing messages, Azure IoT Hub forms the core of these capabilities. It provides support for a range of message protocols, buffering, and scalable message distribution to downstream services. These services include:

• Azure Event Grid for routing incoming events to a variety of handlers, including serverless functions, webhooks, storage queues, and other services
• Azure IoT Central for managing devices, visualizing incoming telemetry on a dashboard, triggering alerts, and integrating with line-of-business applications
• Azure Stream Analytics for simultaneously analyzing aggregated telemetry streams using extended SQL queries to extract patterns that can be fed to workflows, including alerts, serverless functions, and data storage with offline processing
• Azure Time Series Insights for storing time-series data and then exploring, modeling, and querying it to gain insights, such as identifying anomalies and trends, with a rich set of analytics tools
• Azure Digital Twins for creating a graphical representation of the assets within an organization using the Digital Twin Definition Language, processing events, and visualizing entity graphs to display and query status

While Azure IoT offers a wide variety of services, it focuses on visualizing entities and events, extracting insights from telemetry streams with queries, and migrating events to storage for more intensive offline analysis. What’s missing is continuous, real-time introspection on the dynamic state of IoT devices to predict and immediately react to significant changes in their state. These capabilities are vitally important to extract the full potential of real-time intelligent monitoring.

For example, here are some scenarios in which stateful, real-time introspection can create important insights. Telemetry from each truck in a fleet of thousands can provide numerous parameters about the driver (such as repeated lateral accelerations at the end of a long shift) that might indicate the need for a dispatcher to intervene. A health tracking device might indicate a combination of signals (blood pressure, blood oxygen, heart rate, etc.) that indicate an emerging medical issue for an individual with a known medical history and current medications. A security sensor in a key-card access system might indicate an unusual pattern of building entries for an employee who has given notice of resignation.

In all of these examples, the event-processing system needs to be able to independently analyze events for each data source (IoT device) within milliseconds, and it needs immediate access to dynamic, contextual information about the data source that it can use to perform real-time predictive analytics. In short, what’s needed is a scalable, in-memory computing platform connected directly to Azure IoT Hub which can ingest and process event messages separately for each data source using memory-based state information maintained for that data source.

The ScaleOut Digital Twin Streaming Service provides precisely these capabilities. It does this by leveraging the digital twin concept (not to be confused with Azure Digital Twins) to create an in-memory software object for every data source that it is tracking. This object, called a real-time digital twin, holds dynamic state information about the data source and is made available to the application’s event handling code, which runs within 1-2 milliseconds whenever an incoming event is received. Application developers write event handling code in C#, Java, JavaScript, or using a rules engine; this code encapsulates application logic, such as a predictive analytics or machine learning algorithm. Once the real-time digital twin’s model (that is, its state data and event handling code) has been created, the developer can use an intuitive UI to deploy it to the streaming service and connect to Azure IoT Hub.

As shown in the following diagram, ScaleOut’s streaming service connects to Azure IoT Hub, runs alongside other Azure IoT services, and provides unique capabilities that enhance the overall Azure IoT ecosystem:

ScaleOut’s streaming service handles all the details of message delivery, data management, code orchestration, and scalable execution. This makes developing streaming analytics code for real-time digital twins fast and easy. The application developer just focuses on writing a single method to process incoming messages, run application-specific analytics, update state information about the data source, and generate alerts as needed. The optional rules engine further simplifies the development process with a UI for specifying state data and a sequential list of business rules for describing analytics code.

How are the streaming service’s real-time digital twins different from Azure digital twins? Both services leverage the digital twin concept by providing a software entity for each IoT device that can track the parameters and state of the device. What’s different is the streaming service’s focus on real-time analytics and its use of an in-memory computing platform integrated with Azure IoT Hub to ensure the lowest possible latency and high scalability. Azure digital twins serve a different purpose. They are intended to maintain a graphical representation of an organization’s entities for management and querying current status; they are not designed to implement real-time analytics using application-defined algorithms.

The following diagram illustrates the integration of ScaleOut’s streaming service with Azure IoT Hub to provide fast, scalable event handling with low-latency access to memory-based state for all data sources. It shows how real-time digital twins are distributed across multiple virtual servers organized into an in-memory computing cluster connected to Azure IoT Hub. The streaming service uses multiple message queues in Azure IoT Hub to scale message delivery and event processing:

As IoT devices proliferate and become more intelligent, it’s vital that our cloud-based event-processing systems be able to perform continuous and deep introspection in real time. This enables applications to react quickly, effectively, and autonomously to emerging challenges, such as to security threats and safety issues, as well as to new opportunities, such as real-time ecommerce recommendations. While there is an essential role for query and offline analytics to optimize IoT services, the need for highly granular, real-time analytics continues to grow. ScaleOut’s Digital Twin Streaming Service is designed to meet this need as an integral part of the Azure IoT ecosystem.

To learn more about using the ScaleOut’s Digital Twin Streaming Service in the Microsoft Azure cloud, visit the Azure Marketplace here.

The post Adding New Capabilities for Real-Time Analytics to Azure IoT appeared first on ScaleOut Software.

The goal of real-time streaming analytics is to get answers fast. Mission-critical applications that manage large numbers of live data sources need to quickly sift through incoming telemetry, assess dynamic changes, and immediately pinpoint emerging issues that need attention. Examples abound: a telematics application tracking a fleet of vehicles, a vaccine distribution system managing the delivery of thousands of shipments, a security or safety application analyzing entry points in a large infrastructure (physical or cyber), a healthcare application tracking medical telemetry from a population of wearable devices, a financial services application watching wire transfers and looking for potential fraud — the list goes on. In all these cases, when a problem occurs (or an opportunity emerges), managers need answers now.

Conventional streaming analytics platforms are unable to separate messages from each data source and analyze them as they flow in. Instead, they ingest and store telemetry from all data sources, attempt a preliminary search for interesting patterns in the aggregated data stream, and defer detailed analysis to offline batch processing. As a result, they are unable to introspect on the dynamic, evolving state of each data source and immediately alert on emerging issues, such as the impending failure of a truck engine, an unusual pattern of entries and exits to a secure building, or a potentially dangerous pattern of telemetry for a patient with a known medical condition.

In-memory computing with software components called real-time digital twins overcomes these obstacles and enables continuous analysis of incoming telemetry for each data source with contextual information that deepens introspection. While processing each message in a few milliseconds, this technology automatically scales to simultaneously handle thousands of data sources. It also can aggregate and visualize the results of analysis every few seconds so that managers can graphically track the state of a complex live system and quickly pinpoint issues.

The ScaleOut Digital Twin Streaming Service is an Azure-based cloud service that uses real-time digital twins to perform continuous data ingestion, analysis by data source, aggregation, and visualization, as illustrated below. What’s key about this approach is that the system visualizes state information that results from real-time analysis —  not raw telemetry flowing in from data sources. This gives managers curated data that intelligently focuses on the key problem areas (or opportunities). For example, instead of looking at fluctuating oil temperature, telematics dispatchers see the results of predictive analytics. There’s not enough time for managers to examine all the raw data, and not enough time to wait for batch processing to complete. Maintaining situational awareness requires real-time introspection for each data source, and real-time digital twins provide it.

In the ScaleOut Digital Twin Streaming Service, real-time data visualization can take the form of charts and tables. Dynamic charts effectively display the results of aggregate analytics that combine data from all real-time digital twins to show emerging patterns, such as the regions of the country with the largest delivery delays for a vaccine distribution system. This gives a comprehensive view that helps managers maintain the “big picture.” To pinpoint precisely which data sources need attention, users can query analytics results for all real-time digital twins and see the results in a table. This enables managers to ask questions like “Which vaccination centers in Washington state are experiencing delivery delays in excess of 1 hour and have seen more than 100 people awaiting vaccinations at least three times today?” With this information, managers can immediately determine where vaccine shipments should be delivered first.

With the latest release, the streaming service now offers geospatial mapping of query results combined with continuous queries that refresh the map every few seconds. For example, using this cloud service, a telematics system for a trucking fleet can continuously display the locations of specific trucks which have issues (the red dots on the map) in addition to watching aggregate statistics:

For applications like this, a mapped view of query results offers valuable insights about the locations where issues are emerging that would otherwise be more difficult to obtain from a tabular view. Note that the queried data shows the results of real-time analytics which are continuously updated as messages arrive and are processed. For example, instead of displaying the latest oil temperature from a truck, the query reports the results of a predictive analytics algorithm that makes use of several state variables maintained by the real-time digital twin. This declutters the dispatcher’s view so that only alertable conditions are highlighted and demand attention:

The following image shows an example of actual map output for a hypothetical security application that tracks possible intrusions within a nationwide power grid. The goal of the real-time digital twins is to assess telemetry from each of 20K control points in the power grid’s network, filter out false-positives and known issues, and produce a quantitative assessment of the threat (“alert level”). Continuous queries map the results of this assessment so that managers can immediately spot a real threat, understand its scope, and take action to isolate it. The map shows the results of results three continuous queries: high alerts requiring action, medium alerts that just need watching, and offline nodes (with the output suppressed here):

In this scenario a high alert has suddenly appeared in the grid at three locations (Seattle, New York, and Miami) indicating a serious, coordinated attack on the network. By zooming in and hovering over dots in the graph, users can display the detailed query results for each corresponding data source. Within seconds, managers have immediate, actionable information about threat assessments and can quickly visualize the locations and scope of specific threats.

In applications like these and many others, the power of in-memory computing with real-time digital twins gives managers a new means to digest real-time telemetry from thousands of data sources, combine it with contextual information that enhances the analysis, and then immediately visualize the results. This powerful technology boosts situational awareness and helps guide responses much better and faster than was previously possible.

The post Introducing Geospatial Mapping for Real-Time Digital Twins appeared first on ScaleOut Software.

With the ScaleOut Digital Twin Streaming Service, an Azure-hosted cloud service, ScaleOut Software introduced breakthrough capabilities for streaming analytics using the real-time digital twin concept. This new software model enables applications to easily analyze telemetry from individual data sources in 1-3 milliseconds while maintaining state information about data sources that deepens introspection. It also provides a basis for applications to create key status information that the streaming platform aggregates every few seconds to maximize situational awareness. Because it runs on a scalable, highly available in-memory computing platform, it can do all this simultaneously for hundreds of thousands or even millions of data sources.

The unique capabilities of real-time digital twins can provide important advances for numerous applications, including security, fleet telematics, IoT, smart cities, healthcare, and financial services. These applications are all characterized by numerous data sources which generate telemetry that must be simultaneously tracked and analyzed, while maintaining overall situational awareness that immediately highlights problems of concern an/or opportunities of interest. For example, consider some of the new capabilities that real-time digital twins can provide in fleet telematics and vaccine distribution during COVID-19.

To address security requirements or the need for tight integration with existing infrastructure, many organizations need to host their streaming analytics platform on-premises. Scaleout StreamServer® DT was created to meet this need. It combines the scalable, battle-tested in-memory data grid that powers ScaleOut StreamServer with the graphical user interface and visualization features of the cloud service in a unified, on-premises deployment. This gives users all of the capabilities of the ScaleOut Digital Twin Streaming Service with complete infrastructure control.

As illustrated in the following diagram, ScaleOut StreamServer DT installs its management console on a standalone server that connects to ScaleOut StreamServer’s in-memory data grid. This console hosts the graphical user interface that is securely accessed by remote workstations within an organization. It also deploys real-time digital twin models to the in-memory data grid, which hosts instances of digital twins (one per data source) and runs application-defined code to process incoming messages. Message are delivered to the grid using messaging hubs, such as Azure IoT Hub, AWS IoT Core, Kafka, a built-in REST service, or directly using APIs.

The management console installs as a set of Docker containers on the management server. This simplifies the installation process and ensures portability across operating systems. Once installed, users can create accounts to control access to the console, and all connections are secured using SSL. The results of aggregate analytics and queries performed within the in-memory data grid can then be accessed and visualized on workstations running throughout an organization.

Because ScaleOut’s in-memory data grid runs in an organization’s data center and avoids the requirement to use a cloud-hosted message hub or REST service, incoming messages from data sources can be processed with minimum latency. In addition, application code running in real-time digital twins can access local resources, such as databases and alerting systems, with the best possible performance and security. Use of dedicated computing resources for the in-memory data grid delivers the highest possible throughput for message processing and real-time analytics.

While cloud hosting of streaming analytics as a SaaS (software-as-a-service) offering creates clear advantages in reducing capital costs and providing access to highly elastic computing resources, it may not be suitable for organizations which need to maintain full control of their infrastructures to address security and performance requirements. ScaleOut StreamServer DT was designed to meet these needs and deliver the important, unique benefits of streaming analytics using real-time digital twins to these organizations.

The post Deploying Real-Time Digital Twins On Premises with ScaleOut StreamServer DT appeared first on ScaleOut Software.

Simplified Creation of Analytics Logic Lowers the Learning Curve for Using Digital Twins in Streaming Analytics

As discussed in earlier blog posts, real-time digital twins offer a breakthrough new approach to streaming analytics by providing a means for continuously analyzing each incoming telemetry stream from thousands of data sources. Because they maintain state information about each data source, they can immediately spot issues unique to that data source and generate alerts within a few milliseconds. In contrast, conventional “batch-oriented” streaming analytics typically do not mine this telemetry in real-time and may not uncover important, actionable trends for several minutes or hours. These unique capabilities, combined with real-time data aggregation to boost situational awareness, give real-time digital twins unique advantages in a wide range of applications, including contact tracing, telematics, logistics, smart cities, security, financial services, healthcare, and much more.

Real-time digital twins provide a software technique for orchestrating the execution of analytics code that examines incoming messages from a single data source and maintains state information about that data source. The ScaleOut Digital Twin Streaming Service hosts instances of real-time digital twins in the Microsoft Azure cloud or on-premises, manages the delivery of messages from various message hubs, and implements data aggregation and visualization. Application developers typically implement a single method containing analytics code written in standard programming languages, such as Java, C#, and JavaScript, which take full advantage of the object-oriented, real-time digital twin model. Here is a depiction of a real-time digital twin showing the message processing code and state information unique to a specific data source:

Rules-Based Real-Time Digital Twins

In many applications, a rules-based formulation of analytics logic can simplify application code and open up development of real-time digital twins to analysts who lack object-oriented programming experience. Rules-based algorithms have been widely adopted over the years and proven to provide a straightforward technique for expressing business logic in numerous applications and expert systems. In their simplest form, rules are expressed as “IF condition THEN action” statements which are executed sequentially by a “rules engine.” Other rules which just perform actions, such as calculations or message sending, can be expressed with “DO action” statements. These rules replace programming code with simple, highly readable statements that can be used in many applications where more complex logic is not required.

For example, consider an IoT application in which a real-time digital twin is monitoring messages sent from a thermometer and looking for a situation in which the temperature either spikes beyond an allowed limitof 250 deg. or exceeds an allowed average value of 112 deg. This logic could be expressed with the following rules, which are executed for each incoming message. Note that the temperature reading within the message is called Incoming.Temp here, and the other variables maintain state information within the real-time digital twin’s instance for this thermometer. For example, the number of temperature spikes is maintained in the variable NumEvents.

DO CurrentTemp = Incoming.Temp
IF CurrentTemp > MaxTemp THEN MaxTemp = CurrentTemp
DO AverageTemp = AverageTemp * NumSamples + CurrentTemp
DO NumSamples = NumSamples + 1
DO AverageTemp = AverageTemp / NumSamples
IF MaxTemp > 250.0 THEN NumEvents = NumEvents + 1
IF MaxTemp > 250.0 THEN LogMessage.Message = "Max temp exceeded" AND LogMessage
IF AverageTemp > 112.0 THEN LogMessage.Message = "Average temp exceeded" AND LogMessage

The following diagram shows how message are delivered to a thermometer’s real-time digital twin instance and are analyzed by the rules engine:

Development Tool for Building Rules-Based Models

To simplify the development of rules-based analytics code for real-time digital twins, ScaleOut Software has developed the ScaleOut Rules Engine Development Tool. This Windows-based graphical development environment enables application developers to create and test rule-based digital twin models prior to deploying them on the streaming service for production use. Using this tool, developers create a model by specifying:

• Instance properties to be tracked, such as AverageTemp, MaxTemp, and NumEvents in the example
• Message properties that will be used, such as Incoming.Temp for incoming messages
• Rules to be executed (like the ones listed above)

The tool validates the rules when they are created to make sure that they will execute. Next, the user can test the model by sending it messages and observing changes in the values of the properties. The rules can be run one at a time for each message to verify that they are creating the desired state changes and outgoing messages. The development tool can simulate sending message back to the data source, to another real-time digital twin instance, or to the message log in the service’s UI.

Here is a screenshot of the development tool during a test of a rules-based model for a thermometer:

Note that during production use, the streaming service can aggregate instance properties across all real-time digital twin instances and visualize the results. The rules engine running in each real-time digital twin instance updates property values as it processes incoming messages, and the results are immediately aggregated. For example, if the thermometers supplied their locations, the average temperature could be plotted by region. This allows managers to immediately spot patterns in the data across all data sources and direct responses where they are most urgently needed.

Summing Up

The integration of a rules engine within real-time digital twins lowers barriers to entry in creating streaming analytics. The highly intuitive formulation of application logic as a set of rules to be sequentially evaluated makes it straightforward for domain experts to implement streaming analytics for many applications without the need for programming skills. The power of real-time digital twins working together, combined with continuous aggregate analytics, enables telemetry from many thousands of data sources to be simultaneously  analyzed and creates a breakthrough in situational awareness.

The post Building Real-Time Digital Twins with a Rules Engine appeared first on ScaleOut Software.

Real-Time Digital Twins Can Add Important New Capabilities to Telematics Systems and Eliminate Scalability Bottlenecks

Rapid advances in the telematics industry have dramatically boosted the efficiency of vehicle fleets and have found wide ranging applications from long haul transport to usage-based insurance. Incoming telemetry from a large fleet of vehicles provides a wealth of information that can help streamline operations and maximize productivity. However, telematics architectures face challenges in responding to telemetry in real time. Competitive pressures should spark innovation in this area, and real-time digital twins can help.

Current Telematics Architecture

The volume of incoming telemetry challenges current telematics systems to keep up and quickly make sense of all the data. Here’s a typical telematics architecture for processing telemetry from a fleet of trucks:

Each truck today has a microprocessor-based sensor hub which collects key telemetry, such as vehicle speed and acceleration, engine parameters, trailer parameters, and more. It sends messages over the cell network to the telematics system, which uses its compute servers (that is, web and application servers) to store incoming messages as snapshots in an in-memory data grid, also known as a distributed cache.  Every few seconds, the application servers collect batches of snapshots and write them to the database where they can be queried by dispatchers managing the fleet. At the same time, telemetry snapshots are stored in a data lake, such as HDFS, for offline batch analysis and visualization using big data tools like Spark. The results of batch analysis are typically produced after an hour’s delay or more. Lastly, all telemetry is archived for future use (not shown here).

This telematics architecture has evolved to handle ever increasing message rates (often reaching 2K messages per second), make up-to-the-minute information available to dispatchers, and feed offline analytics. Using a database, dispatchers can query raw telemetry to determine the information they need to manage the fleet in real time. This enables them to answer questions such as:

• “Where is truck 7563?”
• “How long has the driver been on the road?”
• “Which trucks have abnormally high oil temperature?”

Offline analytics can mine the telemetry for longer term statistics that help managers assess the fleet’s overall performance, such as the average length of delivery or routing delays, the fleet’s change in fuel efficiency, the number of drivers exceeding their allowed shift times, and the number and type of mechanical issues. These statistics help pinpoint areas where dispatchers and other personnel can make strategic improvements.

Challenges for Current Architectures

There are three key limitations in this telematics architecture which impact its ability to provide managers with the best possible situational awareness. First, incoming telemetry from trucks in the fleet arrives too fast to be analyzed immediately. The architecture collects messages in snapshots but leaves it to human dispatchers to digest this raw information by querying a database. What if the system could separately track incoming telemetry for each truck, look for changes based on contextual information, and then alert dispatchers when problems were identified? For example, the system could perform continuous predictive analytics on the engine’s parameters with knowledge of the engine’s maintenance history and signal if an impending failure was detected. Likewise, it could watch for hazardous driving with information about the driver’s record and medical condition. Having the system continuously introspect on the telemetry for each truck would enable the dispatcher to spot problems and intervene more quickly and effectively.

A second key limitation is the lack of real-time aggregate analysis. Since this analysis must be performed offline in batch jobs, it cannot respond to immediate issues and is restricted to assessing overall fleet performance. What if the real-time telemetry tracking for each truck could be aggregated within seconds to spot emerging issues that affect many trucks and require a strategic response? These issues could include:

• Unexpected delays in a region due to highway blockages or weather that indicate the need to inform or reroute several trucks
• An unusually large number of soon-to-be timed-out drivers or impending maintenance issues which require making immediate schedule changes to avoid downtime
• Congregated drivers who are impacting on-time deliveries

The current telematics architecture also has inherent scalability issues in the form of network bottlenecks. Because all telemetry is stored in the in-memory data grid and accessed by a separate farm of compute servers, the network between the grid and the server farm can quickly bottleneck as the incoming message rate increases. As the fleet size grows and the message rate per truck increases from once per minute to once per second, the telematics system may not be able to handle the additional incoming telemetry.

Solution: Real-Time Digital Twins

A new software architecture for streaming analytics based on the concept of real-time digital twins can address these challenges and add significant capabilities to telematics systems. This new, object-oriented software technique provides a memory-based orchestration framework for tracking and analyzing telemetry from each data source. It comprises message-processing code and state variables which host dynamically evolving contextual information about the data source. For example, the real-time digital twin for a truck could look like this:

Instead of just snapshotting incoming telemetry, real-time digital twins for every data source immediately analyze it, update their state information about the truck’s condition, and send out alerts or commands to the truck or to managers as necessary. For example, they can track engine telemetry with knowledge of the engine’s known issues and maintenance history. They can track position, speed, and acceleration with knowledge of the route, schedule, and driver (allowed time left, driving record, etc.). Message-processing code can incorporate a rules engine or machine learning to amplify their capabilities.

Real-time digital twins digest raw telemetry and enable intelligent alerting in the moment that assists both drivers and dispatchers in surfacing issues that need immediate attention. They are much easier to develop than typical streaming analytics applications, which have to sift through the telemetry from all data sources to pick out patterns of interest and which lack contextual information to guide them. Because they are implemented using in-memory computing techniques, real-time digital twins are fast (typically responding to messages in a few milliseconds) and transparently scalable to handle hundreds of thousands of data sources and message rates exceeding 100K messages/second.

Here’s a depiction of real-time digital twins running within an in-memory data grid in a telematics architecture:

In addition to fitting within an overall architecture that includes database query and offline analytics, real-time digital twins enable built-in aggregate analytics and visualization. They provide curated state information derived from incoming telemetry that can be continuously aggregated and visualized to boost situational awareness for managers, as illustrated below. This opens up an important new opportunity to aggregate performance indicators needed in real time, such as emerging road delays by region or impending scheduling issues due to timed out drivers, that can be acted upon while new problems are still nascent. Real-time aggregate analytics add significant new capabilities to telematics systems.

Summing Up

While telematics systems currently provide a comprehensive feature set for managing fleets, they lack the important ability to track and analyze telemetry from each vehicle in real time and then aggregate derived information to maintain continuous situational awareness for the fleet. Real-time digital twins can address these shortcomings with a powerful, fast, easy to develop, and highly scalable software architecture. This new software technique has the potential to make a major impact on the telematics industry.

To learn more about real-time digital twins in action, take a look at ScaleOut Software’s streaming service for hosting real-time digital twins in the cloud or on-premises here.

The post Use Digital Twins for the Next Generation in Telematics appeared first on ScaleOut Software.

Web applications, such as ecommerce sites and financial services, often need to replicate fast-changing, in-memory data across multiple data centers or cloud regions. As part of an overall strategy for disaster recovery, cross-site data replication ensures that mission-critical data is continuously available, even if one site goes offline.

Many applications need to use two (and sometimes more) sites in an “active-active” manner, distributing the workload across the sites. Here are some real-world applications we have seen. Ecommerce applications need to maintain shopping carts at multiple sites and distribute the workload from their shoppers with a global load-balancer. Cell phone providers need to keep their lists of available mobile numbers consistent across sites as individual stores allocate them. Conference-management companies need to keep attendee lists and schedules consistent at conference sites and their central data center.

Let’s take a closer look at an ecommerce site using a global load-balancer to distribute incoming web requests to multiple sites. This approach lets the web application take advantage of the processing power at multiple sites during normal operations. However, it creates the challenge of coordinating access to in-memory objects which are replicated across two or more sites. This can add substantial complexity if handled by the application.

Here’s an example of an ecommerce site using a global load-balancer to distribute incoming web requests across two sites, each of which hosts shopping carts within an in-memory data grid (also called a distributed cache), such as ScaleOut StateServer®. A web shopper might select a pair of shoes and place them in the shopping cart followed by selecting a tennis racket. As shown in the following diagram, the global load-balancer sends the first request to site 1 and the second request to site 2 in this example:

After the first request completes, the in-memory data grid at site 1 replicates the cart to site 2. The global load-balancer then sends the second request to site 2, which adds the tennis racket to the cart. Finally, site 2 replicates the changes back to site 1 so that both sites have the latest copy of the shopping cart.

What happens if replication from site 1 to site 2 is slightly delayed? After site 2 puts the tennis racket in the cart, the incoming replicated update arrives and overwrites the cart. This causes both sites to lose the update at site 2, and the shopper will undoubtedly be annoyed to find that the tennis racket is missing from the cart:

The solution to this problem is to have the web applications at both sites synchronize updates to the shopping carts. This ensures that only one site at a time updates the shopping cart and that each site always sees the latest version of the in-memory object. Using ScaleOut GeoServer Pro, applications can use standard object-locking APIs for this purpose, just as they would to coordinate object access within a single in-memory data grid:

After the web application on site 1 updates and unlocks object A (the shopping cart in our example), site 1 replicates the update to site 2. When the global load-balancer sends the next request to site 2, the web application on that site 2 also locks and reads the object, updates it, and then unlocks it:

When the object is locked on site 2, ScaleOut GeoServer Pro makes sure that the application sees the latest version of the object. It does so by migrating ownership of the object to site 2 and checking that it has the latest version. Although this requires a round trip to site 1, once a site gains ownership, all further accesses are local until the other site again attempts to lock the object and request ownership. If the global load-balancer avoids ping-ponging between sites with every web request, the latency to lock an object remains low.

Should the wide area network (WAN) connecting the two sites fail, or if the remote site goes offline, the two sites can operate independently; this is called “split brain” mode in distributed systems. They detect the WAN failure and automatically promote local replica objects as needed to gain ownership when requesting a lock. This enables uninterrupted operations that make use of object replicas held at each site. By combining object replication with synchronized access, applications enjoy the full benefits of synchronized object access across sites during normal operations and uninterrupted access during WAN or site outages:

A key challenge created by split-brain mode is how to restore normal operations after an outage has been corrected. For example, the following diagram shows the two sites in our shopping example operating independently during a WAN outage that occurs between the two web requests. Site 1 adds the shoes to its shopping cart but is unable to replicate that update to site 2. The web application on site 2 then places the tennis racket in its shopping cart:

After the WAN is restored, the two sites have to resolve the differences in the contents of their copies of stored objects. Unless the application uses special, conflict-free data types that can be merged (and this is rare for most applications), a heuristic needs to be used to resolve conflicts. ScaleOut GeoServer Pro automatically resolves conflicts for each pair of object copies by selecting the copy with the latest update time or randomly picking one of the copies if the update times are the same. So in this case, both sites are updated with the version of the shopping cart holding the tennis racket. (This will be another source of annoyance for our shopper, but at least the ecommerce site survived a WAN outage without interruption.)

ScaleOut GeoServer Pro resolves split-brain conflicts as it detects them when updates are performed and then are successfully replicated across the WAN. It also has to resolve the fact that both sites now think they own the same object, and it handles this by randomly picking a site to retain ownership. As the two sites attempt to lock and read the object, ownership will then automatically migrate to the site where it’s needed.

One more key benefit of ScaleOut GeoServer Pro is that it lets applications efficiently access objects that have slowly changing contents (such as product descriptions, schedules, and portfolio lists) without making repeated WAN accesses. Sites that are configured for bi-directional replication have immediate access to replicas when just reading but not updating remote objects. Other sites can be configured to maintain local copies of remote objects (called “proxies”) that can periodically poll for updates using a configurable timeout. This minimizes WAN accesses while allowing applications to track changes in objects stored at remote sites.

To illustrate how all of these features can work together, the following diagram shows two sites on the west coast of the U.S. configured for bi-directional replication and synchronized access along with additional “satellite” sites in other states that are periodically polling to read data held in the “live” data centers:

With its advanced capabilities for combining data replication with synchronized access, ScaleOut GeoServer Pro takes a leadership position among commercial in-memory data grids by enabling applications to seamlessly access and update objects replicated across data centers. This solves a long-standing challenge for applications that actively maintain mission-critical data at multiple sites and further extends the power of in-memory data grids to manage fast-changing business data.

The post Combine Data Replication Across Sites with Synchronized Access appeared first on ScaleOut Software.

Also read our Partner Perspective in the same issue, which explains how the Microsoft Azure cloud provides a powerful platform for hosting the ScaleOut Digital Twin Streaming Service and ensures high performance across a wide range of applications.

The post ScaleOut Discusses Contact Tracing in The Record appeared first on ScaleOut Software.

Check out this new video which depicts the challenges in using  conventional tools for streaming analytics to track and respond to thousands of data sources in a live system. Whether you are keeping track of a fleet of trucks or sensors in a smart city, the overwhelming amount of incoming telemetry from countless data sources can create a “data monster” that threatens your ability to perform real-time monitoring and maintain the necessary situational awareness.

As the video shows, ScaleOut’s real-time digital twins running in the ScaleOut Digital Twin Streaming Service can tame your data monster by separately tracking each data source using dynamic state information. They enable fast introspection on dynamic changes and immediate, focused responses. In addition, real-time digital twins continuously gather information which the streaming service can aggregate and visualize in real time to quickly surface issues and enable strategic responses.

Grab your popcorn and then click on the image below to watch the video:

We hope you enjoyed the video. Here’s how to learn more:

• To learn more about the value of real-time digital twins in streaming analytics, click here.
• To learn more about the ScaleOut Digital Twin Streaming Service, click here.
• For detailed technical information, take a look at the User Guide here.
• To contact us and talk about how real-time digital twins can help tame your data monster, click here.

The post ScaleOut Software Releases New Video on Real-Time Digital Twins appeared first on ScaleOut Software.

Watch the video here.

The post Founder & CEO William Bain Discusses Real-Time Digital Twins with TechStrong TV appeared first on ScaleOut Software.

Until a COVID-19 vaccine is widely available, getting back to work means keeping a close watch for outbreaks and quickly containing them when they occur. While the prospects for accomplishing this within large companies seem daunting, tracking contacts between employees may be much easier than for the public at large. This blog post explains how a software application built with a new software construct called real-time digital twins makes this possible.

Tracking Employees Using Real-Time Digital Twins

In an earlier blog post, we saw how real-time digital twins running in the ScaleOut Digital Twin Streaming Service can be used to track employees within a large company using a technique called “voluntary self-tracing.” In this post, we’ll take a closer look at its implementation in a demo application created by ScaleOut Software. We’ll also look at a companion mobile app that allows employees to log contacts with colleagues outside their immediate teams and to notify the company and their contacts if they test positive for COVID-19.

The demo application creates a memory-based real-time digital twin for each employee. Using information from the company’s organizational database, it populates each twin with the employee’s ID, team ID, department type, and location. The twin also keeps a list of the employee’s contacts within the organization (as well as community contacts, discussed below). This allows immediate colleagues and their contacts to be notified if an employee tests positive. The following diagram illustrates an employee’s real-time digital twin and the state data it holds; details about the contact tracing code are explained below:

The twin automatically populates its contact list with the other members of the employee’s team, based on the expectation that team members are in daily contact. Using the mobile app, employees can log one-time and recurring contacts with colleagues in other teams, possibly at different office locations. In addition, they can log contacts outside the company, such as taxi rides, airline flights, and meals at restaurants, so that community members can be notified if an employee was exposed to COVID-19.

An employee can use the mobile app to notify their real-time digital twin of a positive test for COVID-19. Code running in the twin then sends messages to the real-time digital twins for all contacts in the employee’s list. These twins in turn send messages to their contacts, and so on, until the twins for all contacts have been notified. (The algorithm avoids unnecessary messages to team members and circular paths among twins.) The twin then sends a push notification to each affected employee through the mobile app, alerting them to the possible exposure and the number of intermediate contacts between themselves and the infected person. Because real-time digital twins are hosted in memory, all of this happens within seconds, enabling affected employees to immediately self-quarantine and obtain COVID-19 tests.

Here’s an illustration of the chain of contacts originating with an employee who reports testing positive. (Note that the outbound notifications from the twins to the employees’ mobile devices are not shown here.)

What’s in the Real-Time Digital Twin?

As illustrated in the first diagram, each real-time digital twin hosts two components, state data and a message-processing method. These are defined by the contact tracing application and can be written in C#, Java, or JavaScript. (C# was used for the demo application.) The state data is unique for each employee and contains the employee’s information and contact list, along with useful statistics, such as how often the employee has been alerted about a possible exposure. The message-processing method’s code is shared by all twins. It receives messages from the mobile app or from other twins (each corresponding to a single employee) and uses application-defined code to process these messages.

Messages from the mobile app can request to add or remove a contact from the list. For new contacts, they include parameters such as the employee ID of the contact and whether the contact will be recurring. (Users also can record contacts using calendar events.) Messages from the mobile app can also request the current contact list for display, signal that the employee has tested positive or negative, and request current notifications. Messages from other real-time digital twins signal that the corresponding employees have been exposed and provide additional information, such as the number of intermediate contacts and the location of the initial employee who tested positive.

The application’s message-processing code responds to these messages and implements the spanning-tree notification algorithm that alerts other twins on the contact list. The streaming service handles the rest, namely the details of message delivery, retrieval and updating of state information, and managing the execution platform.

Using the Mobile App

The following animated diagram shows how an employee can add a contact with a company colleague outside of their immediate team or with a community contact during business travel (left screenshot). If the employee tests positive, the employee can use the mobile app to report this to the company (middle screenshot). All employees are then notified using the mobile app, as shown in the right screenshot. Community contacts are reported to managers who communicate with outside points of contact, such as airlines, taxi companies, and restaurants.

Using Aggregate Statistics to Spot Outbreaks

The streaming service has the built-in capability to aggregate state data from all real-time digital twins. The service then displays the results in charts which are recalculated every few seconds. These charts enable managers to identify emerging issues, such as an outbreak within a specific department or site. With this information, they can take immediate steps to contain the outbreak and minimize the number of affected employees.

To illustrate the value of aggregate statistics in boosting situational awareness, consider a hypothetical company with 30,000 employees and offices in several states across the U.S. Suppose an employee at the Texas site suddenly tests positive. This could be immediately alerted to managers with the following chart generated and continuously updated by the streaming service, which shows all employees who have tested positive:

Within a few seconds, the real-time digital twins notify all points of contact. Updates to state data are immediately aggregated in another chart that shows the sites where employees have been notified of a positive contact and the number of employees affected at each site:

This chart shows that about 140 employees in three states were notified and possibly exposed directly or indirectly. All of these employees are then immediately quarantined to contain the possible spread of COVID-19. After an investigation by company managers, it is determined that the employee had business travel to Arizona and met with a team that subsequently had business travel to California. Instead of taking hours or days to uncover the scope of a COVID-19 exposure, contact tracing using real-time digital twins alerts managers within seconds.

The real-time digital twins can collect additional useful statistics for visualization by the streaming service. Another chart can show the average number of intermediate contacts for all notified employees, which is an indication of how widely employees have been interacting across teams. If this becomes an issue (as it is in the above example), managers can implement policies to further isolate teams. As shown below, a chart can also show the number of notified employees by department so that managers can determine whether certain departments, such as retail outlets, need stricter policies to limit exposure to COVID-19 from outside contacts.

The Benefits of an Integrated Streaming Service

This contact tracing application demonstrates the power of real-time digital twins to enable fast application development with compelling benefits. Because the amount of application code is small, real-time digital twins can be quickly written and tested. (See a recent blog post which describes how to simplify debugging and testing using a mock environment prior to deployment in the cloud.) They also can be easily modified and updated.

The ScaleOut Digital Twin Streaming Service provides the execution platform so that the application code does not have to deal with message distribution, state saving, performance scaling, and high availability. It also includes support for real-time aggregate analytics and visualization integrated with the real-time digital twin model to maximize ease of use.

Compare this approach to the complexity of building out an application server farm, database, analytics application, and visualization to accomplish the same goals at higher cost and lower performance. Cobbling together these diverse technologies would require several skill sets, lengthy development time, and higher operational costs.

Summing Up

This demo contact tracing application was designed to show how companies can take advantage of their organizational structures to track contacts among employees and quickly notify all affected employees when an individual tests positive for COVID-19. By responding quickly to an exposure with immediate, comprehensive information about its extent within the company (and with community contacts), managers can limit the exposure’s impact. The application also shows how the real-time digital twin model enables a quick, agile implementation which can be easily adapted to the specific needs of a wide range of companies.

Please contact us at ScaleOut Software to learn more about this demo application for limiting the impact of COVID-19 and other ways real-time digital twins can help your company monitor and respond to fast-changing events.

The post Using Real-Time Digital Twins for Corporate Contact Tracing appeared first on ScaleOut Software.

What Problems Does Streaming Analytics Solve?

To understand why we need real-time digital twins for streaming analytics, we first need to look at what problems are tackled by popular streaming platforms. Most if not all platforms focus on mining the data within an incoming message stream for patterns of interest. For example, consider a web-based ad-serving platform that selects ads for users and logs messages containing a timestamp, user ID, and ad ID every time an ad is displayed. A streaming analytics platform might count all the ads for each unique ad ID in the latest five-minute window and repeat this every minute to give a running indication of which ads are trending.

Based on technology from the Trill research project, the Microsoft Stream Analytics platform offers an elegant and powerful platform for implementing applications like this. It views the incoming stream of messages as a columnar database with the column representing a time-ordered history of messages. It then lets users create SQL-like queries with extensions for time-windowing to perform data selection and aggregation within a time window, and it does this at high speed to keep up with incoming data streams.

Other streaming analytic platforms, such as open-source Apache Storm, Flink, and Beam and commercial implementations such as Hazelcast Jet, let applications pass an incoming data stream through a pipeline (or directed graph) of processing steps to extract information of interest, aggregate it over time windows, and create alerts when specific conditions are met. For example, these execution pipelines could process a stock market feed to compute the average stock price for all equities over the previous hour and trigger an alert if an equity moves up or down by a certain percentage. Another application tracking telemetry from gas meters could likewise trigger an alert if any meter’s flow rate deviates from its expected value, which might indicate a leak.

What’s key about these stream-processing applications is that they focus on examining and aggregating properties of data communicated in the stream. Other than by observing data in the stream, they do not track the dynamic state of the data sources themselves, and they don’t make inferences about the behavior of the data sources, either individually or in aggregate. So, the streaming analytics platform for the ad server doesn’t know why each user was served certain ads, and the market-tracking application does not know why each equity either maintained its stock price or deviated materially from it. Without knowing the why, it’s much harder to take the most effective action when an interesting situation develops. That’s where real-time digital twins can help.

The Need for Real-Time Digital Twins

Real-time digital twins shift the application’s focus from the incoming data stream to the dynamically evolving state of the data sources. For each individual data source, they let the application incorporate dynamic information about that data source in the analysis of incoming messages, and the application can also update this state over time. The net effect is that the application can develop a significantly deeper understanding about the data source so that it can take effective action when needed. This cannot be achieved by just looking at data within the incoming message stream.

For example, the ad-serving application can use a real-time digital twin for each user to track shopping history and preferences, measure the effectiveness of ads, and guide ad selection. The stock market application can use a real-time digital twin for each company to track financial information, executive changes, and news releases that explain why its stock price starts moving and filter out trades that don’t fit desired criteria.

Also, because real-time digital twins maintain dynamic information about each data source, applications can aggregate this highly curated data instead of just aggregating data in the data stream. This gives users deeper insights into the overall state of all data sources and boosts “situational awareness” that is hard to maintain by just looking at the message stream.

An Example

Consider a trucking fleet that manages thousands of long-haul trucks on routes throughout the U.S. Each truck periodically sends telemetry messages about its location, speed, engine parameters, and cargo status (for example, trailer temperature) to a real-time monitoring application at a central location. With traditional streaming analytics, personnel can detect changes in these parameters, but they can’t assess their significance to take effective, individualized action for each truck. Is a truck stopped because it’s at a rest stop or because it has stalled? Is an out-of-spec engine parameter expected because the engine is scheduled for service or does it indicate that a new issue is emerging? Has the driver been on the road too long? Does the driver appear to be lost or entering a potentially hazardous area?

The use of real-time digital twins provides the context needed for the application to answer these questions as it analyzes incoming messages from each truck. For example, it can keep track of the truck’s route, schedule, cargo, mechanical and service history, and information about the driver. Using this information, it can alert drivers to impending problems, such as road blockages, delays or emerging mechanical issues. It can assist lost drivers, alert them to erratic driving or the need for rest stops, and help when changing conditions require route updates.

The following diagram shows a truck communicating with its associated real-time digital twin. (The parallelogram represents application code.) Because the twin holds unique contextual data for each truck, analysis code for incoming messages can provide highly focused feedback that goes well beyond what is possible with traditional streaming analytics:

As illustrated below, the ScaleOut Digital Twin Streaming Service runs as a cloud-hosted service in the Microsoft Azure cloud to provide streaming analytics using real-time digital twins. It can exchange messages with thousands of trucks across the U.S., maintain a real-time digital twin for each truck, and direct messages from that truck to its corresponding twin. It simplifies application code, which only needs to process messages from a given truck and has immediate access to dynamic, contextual information that enhances the analysis. The result is better feedback to drivers and enhanced overall situational awareness for the fleet.

Lower Complexity and Higher Performance

While the functionality implemented by real-time digital twins can be replicated with ad hoc solutions that combine application servers, databases, offline analytics, and visualization, they would require vastly more code, a diverse combination of skill sets, and longer development cycles. They also would encounter performance bottlenecks that require careful analysis to measure and resolve. The real-time digital twin model running on ScaleOut Software’s integrated execution platform sidesteps these obstacles.

Scaling performance to maintain high throughput creates an interesting challenge for traditional streaming analytics platforms because the work performed by their task pipelines does not naturally map to a set of processing cores within multiple servers. Each pipeline stage must be accelerated with parallel execution, and some stages require longer processing time than others, creating bottlenecks in the pipeline.

In contrast, real-time digital twins naturally create a uniformly large set of tasks that can be evenly distributed across servers. To minimize network overhead, this mapping follows the distribution of in-memory objects within ScaleOut’s in-memory data grid, which holds the state information for each twin. This enables the processing of real-time digital twins to scale transparently without adding complexity to either applications or the platform.

Summing Up

Why use real-time digital twins? They solve an important challenge for streaming analytics that is not addressed by other, “pipeline-oriented” platforms, namely, to simultaneously track the state of thousands of data sources. They use contextual information unique to each data source to help interpret incoming messages, analyze their importance, and generate feedback and alerts tailored to that data source.

Traditional streaming analytics finds patterns and trends in the data stream. Real-time digital twins identify and react to important state changes in the data sources themselves. As a result, applications can achieve better situational awareness than previously possible. This new way of implementing streaming analytics can be used in a wide range of applications. We invite you to take a closer look.

The post Why Use “Real-Time Digital Twins” for Streaming Analytics? appeared first on ScaleOut Software.

In-Memory Data Grids for Fast-Changing Data

For more than fifteen years, ScaleOut StateServer® has demonstrated technology leadership as an in-memory data grid (IMDG) and distributed cache. Designed to help scalable applications deliver high performance, it stores live, fast-changing data in memory (DRAM) for fast updates and retrieval. By transparently distributing stored objects across a cluster of servers (physical or virtual), it automatically scales performance for fast-growing workloads and maintains consistently low access latency. Typical uses include storing session-state and ecommerce shopping carts, product descriptions, airline reservations, financial portfolios, news stories, online learning data, and many others.

From its inception, the design philosophy behind ScaleOut StateServer has been to simultaneously maximize both performance and ease of use. Because IMDGs have complex internal mechanisms, they need to automate them as much as possible so that the developer can just focus on application concerns and not on the inner workings of the IMDG. For this reason, the product incorporates features such as automatic discovery of servers, transparent load-balancing when servers are added to the cluster or removed, automatic data replication for high availability with transparent placement of replicas, quorum-based updating of replicas to ensure consistency, integrated client libraries, and coherent client-side caching. The net effect is that applications maintain a straightforward view of the IMDG as a unified key/value store for serialized application objects.

The Challenges with Parallel Queries

Although IMDGs are optimized for key-based access, applications often need to retrieve groups of objects with matching properties. For example, if an application is storing shopping carts, it might be useful to find all shopping carts with a total value that exceeds a specified threshold so that these shoppers can be given special attention. To this end, ScaleOut StateServer incorporates a property-based, distributed query API that returns a collection of matching objects. To simplify development for .NET applications, it uses Microsoft’s language integrated query (LINQ) to specify queries. (Java applications use a similar mechanism.)

Queries in an IMDG can create interesting performance challenges. Because IMDGs have highly scalable storage capacity, they can easily return large numbers of matching objects to the client application, and this leads to network bottlenecks transferring large amounts of data from the IMDG back to the client. Once all objects are delivered, the client is then faced with the task of analyzing potentially huge numbers of objects. This can saturate the client’s CPU and delay responses, as illustrated in the following diagram:

ScaleOut StateServer Pro: Integrated Data Analytics

To address these challenges, ScaleOut Software has introduced ScaleOut StateServer Pro, an advanced version of ScaleOut StateServer that integrates data analytics within the IMDG. Instead of querying objects from the IMDG and analyzing them in the client, applications can now simply run this analysis within the IMDG itself using APIs available in ScaleOut StateServer Pro. Because all the work is performed with the IMDG, this has the two-fold advantage of offloading both the network and the client’s CPU. It also transparently makes use of the IMDG’s scalable computing resources to accelerate the analysis.

Take a look at how integrated data analytics can help client applications. In the following illustration, the client library sends the application’s analysis method (“Analyze”) to the IMDG for execution in parallel on all shopping carts selected by a query. The results are combined within the IMDG and returned to the application:

Keeping with the design philosophy of maximizing both performance and ease of use, ScaleOut StateServer Pro lets developers easily construct data analytics by specifying an object-oriented method that analyzes each matching object selected by a query and a second method for combining the results. In .NET applications, this data-parallel execution structure can be described using a distributed version of Microsoft’s popular Parallel.ForEach API, which ScaleOut StateServer Pro integrates with LINQ query. Application code is automatically shipped by the client library to the IMDG for execution and runs fully in parallel across all servers for maximum performance.

Consider the above example of querying shopping carts exceeding a threshold value. Suppose the application’s goal is to periodically analyze high value shopping carts to make upsell offers based on the contents of each cart. Instead of querying the IMDG and returning thousands of shopping carts to the client, the application can implement a method which analyzes these carts within the IMDG to determine which carts should receive upsell offers (and possibly determine which upsell offers to make). This analysis runs in parallel within the IMDG and then returns its results to the client for further action. This dramatically reduces the workload on the network and client, and it ensures consistently high performance.

Summing Up: Extracting Maximum Value from an IMDG

Since their inception, IMDGs have to a large extent been underutilized by viewing them as passive key/value stores. Because they are actually designed as a data-parallel execution platform, they can do much more than just store and serve memory-hosted, live data. They also can perform analysis quickly and efficiently — where the data lives.

Taking full advantage of this powerful capability requires just a shift in thinking about where application work should be performed. In many cases, it’s a much better choice to analyze data within the IMDG instead of transferring it to the client for analysis. ScaleOut StateServer Pro makes it easy to do just that, and it delivers fast, scalable performance. Now developers can finally extract full value from their IMDGs.

The post The Power of Integrated Analytics Within an IMDG appeared first on ScaleOut Software.

Going back to the mid-1990s, online systems have seen relentless, explosive growth in usage, driven by ecommerce, mobile applications, and more recently, IoT. The pace of these changes has made it challenging for server-based infrastructures to manage fast-growing populations of users and data sources while maintaining fast response times. For more than two decades, the answer to this challenge has proven to be a technology called in-memory computing.

In general terms, in-memory computing refers to the related concepts of (a) storing fast-changing data in primary memory instead of in secondary storage and (b) employing scalable computing techniques to distribute a workload across a cluster of servers. Assuming bottlenecks are avoided, this enables transparent throughput scaling that matches an increase in workload, which in turn keeps response times low for users. It can also take advantage of the elastic computing resources available in cloud infrastructures to quickly and cost-effectively scale throughput to meet changes in demand.

Harnessing the power of in-memory computing requires software platforms that can make in-memory computing’s scalability readily available to applications using APIs while hiding the complexity of its implementation. Emerging in the early 2000s, the first such platforms provided distributed caching on clustered servers with straightforward APIs for storing and retrieving in-memory objects. When first introduced, distributed caching offered a breakthrough for applications by storing fast-changing data in memory on a server cluster for consistently fast response times, while simultaneously offloading database servers that would otherwise become bottlenecked. For example, ecommerce applications adopted distributed caching to store session-state, shopping carts, product descriptions, and other data that shoppers need to be able to access quickly.

Software platforms for distributed caching, such as ScaleOut StateServer®, which was introduced in 2005, hide internal mechanisms for cluster membership, throughput scaling, and high availability to take full advantage of the cluster’s scalable memory without adding complexity to applications. They transparently distribute stored objects across the cluster’s servers and ensure that data is not lost if a server or network component fails.

As distributed caching has evolved over the last two decades, additional mechanisms for in-memory computing have been incorporated to take advantage of the computing power available in the server cluster. Parallel query enables stored objects on all servers to be scanned simultaneously to retrieve objects with desired properties. Data-parallel computing analyzes objects on the server cluster to extract and report patterns of interest; it scales much better than parallel query by avoiding network bottlenecks and by using the cluster’s computing resources.

Most recently, stream-processing has been implemented with in-memory computing to simultaneously analyze telemetry from thousands or even millions of data sources and track dynamic state information for each data source. ScaleOut Software’s real-time digital twin model provides straightforward APIs for implementing stream-processing applications within its ScaleOut Digital Twin Streaming Service, an Azure-based cloud service, while hiding internal mechanisms, such as distributing incoming messages to in-memory objects, updating state information for each data source, and running aggregate analytics.

The following diagram shows the evolution of in-memory computing from distributed caching to stream-processing with real-time digital twins. Each step in the evolution has built on the previous one to add new capabilities that take advantage of the scalable computing power and fast data access that in-memory computing enables.

For ecommerce applications, this evolution has created new capabilities that dramatically improve the experience for online shoppers. Instead of just passively hosting session-state and shopping carts, online applications now can mine shopping carts for dynamic trends to evaluate the effectiveness of product descriptions and marketing programs (such as flash sales). They can also employ real-time digital twins or similar techniques to track each shopper’s behavior and make recommendations. By analyzing a click-stream of product selections in the context of knowledge of a shopper’s preferences and demographics, an ecommerce site can make highly focused recommendations to assist the shopper.

For example, one of ScaleOut Software’s customers recently upgraded from just using distributed caching to scale its ecommerce application. This customer now incorporates stream-processing capabilities using ScaleOut StreamServer® to capture click-streams and score users so that its web site can make more effective real-time offers.

The following diagram illustrates how the evolution of in-memory computing has enhanced the online experience for ecommerce shoppers by providing in-the-moment suggestions:

Starting with its development for parallel supercomputing in the late 1990s and evolving into its latest form as a cloud-based service, in-memory computing has offered powerful, software based APIs for building applications that serve large populations of users and data sources. It has helped assure that these applications deliver predictably fast performance and scale to meet the demands of growing workloads. In the next few years, we should continued innovation from in-memory computing to help ecommerce and other applications maintain their competitive edge.

The post The Amazing Evolution of In-Memory Computing appeared first on ScaleOut Software.