DEVOPSdigest

ScaleOut Software introduces generative AI and machine-learning (ML) powered enhancements to its ScaleOut Digital Twins™ cloud service and on-premises hosting platform with the release of Version 4.

This latest release introduces generative AI integration through OpenAI’s large language model, significantly expanding the ability of digital twins to analyze data, detect anomalies and provide real-time insights when monitoring complex live systems. By leveraging these capabilities, operations managers can quickly pinpoint and address emerging issues while reducing their workload. Version 4 also adds automatic retraining for ML algorithms running within digital twins, continuously improving their monitoring capabilities as they process new telemetry data.

ScaleOut's Version 4 generative AI and ML features move real-time monitoring towards fully autonomous operations that boost both safety and efficiency in managing large, complex systems. This technology can be applied across numerous industries, including transportation networks, security systems, smart cities, and military asset tracking.

“ScaleOut Digital Twins Version 4 marks a pivotal step in harnessing AI and machine learning for real-time operational intelligence,” said Dr. William Bain, CEO and founder of ScaleOut Software. “By integrating these technologies, we’re transforming how organizations monitor and respond to complex system dynamics — making it faster and easier to uncover insights that would otherwise go unnoticed. This release is about more than just new features; it's about redefining what’s possible in large-scale, real-time monitoring and predictive modeling.”

Key Features and Benefits of ScaleOut Digital Twins, Version 4:

- Perform Automatic Anomaly Detection with Generative AI: Enables users to leverage generative AI for continuous, real-time anomaly detection. By seamlessly sending aggregated data from digital twins to OpenAI’s large language model, the platform can now identify spikes, trends, and unusual patterns across historical data streams. This feature automates the real-time monitoring process, enabling faster detection of emerging issues while freeing operations managers from constant dashboard surveillance — allowing them to focus on addressing problems rather than searching for them.

- Easily Create Data Visualizations and Queries with Natural Language Prompts: Generative AI now allows users to explore and visualize aggregated digital twin data by simply describing their requirements using natural language prompts. This streamlines operations managers' workflows by allowing AI to assist in creating insightful visualizations and queries quickly and efficiently — reducing the need to construct queries manually.

- Automatically Retrain ML Algorithms in Live Systems: Digital twins now take machine learning to the next level by not only detecting anomalies in live telemetry data but also automatically retraining ML algorithms on the fly. By working together, digital twins can generate and use real-time data to retrain ML algorithms without interrupting operations. Users also have the option to access this retraining data for manual retraining and redeployment. This capability ensures that ML algorithms continuously evolve and adapt to changing conditions, delivering smarter, faster, and more reliable insights as they process live data.

- Additional Collaboration & Performance Enhancements: ScaleOut Digital Twins now incorporates ML algorithms from TensorFlow in addition to Microsoft ML.NET, offering users more options for deploying machine learning models. Numerous performance improvements enable the product’s in-memory computing platform to demonstrate handling workloads using more than 3 million digital twins to continuously analyze more than 100 thousand messages per second from different data sources. Digital twins can also now quickly access and share data using an in-memory data grid.

Application developers can take advantage of ScaleOut's open-source APIs to construct digital twin models for real-time monitoring and simulation on the ScaleOut Digital Twins platform. To streamline development, an open-source workbench allows developers to test applications before deploying them across thousands of digital twins.

Built on highly scalable, in-memory computing technology, the platform supports the live analysis of data from IoT devices and other sources, delivering actionable insights in seconds. It also runs large-scale simulations to optimize the design and operation of complex systems such as transportation networks, logistics operations, military scenarios, and smart cities.