Digital twins have been used for several years in product life cycle management to help design complex new devices. With recent advances in scalable, in-memory computing, their application to live systems for operational monitoring has now been made possible. Unlike traditional stream-processing systems which focus on extracting patterns from incoming telemetry, digital twins can maintain contextual information about each data source. This enables deeper introspection than previously possible and leads to significantly more effective feedback — all within milliseconds.
For example, an IoT predictive analytics application attempting to avoid an impending failure in a population of medical freezers must look at more than just trends in temperature readings. It needs to evaluate these readings in the context of each freezer’s operational history, recent maintenance, and current state to get a complete picture of the freezer’s actual condition. Digital twins can make use of this contextual information to analyze telemetry and make better real-time decisions.
ScaleOut’s in-memory computing platform delivers messages to digital twins within milliseconds and eliminates bottlenecks in accessing contextual data.
Applications can continuously combine data from multiple digital twins to quickly identify areas of concern and maximize situational awareness.
Run digital twins in the Microsoft Azure cloud or on-premises. Seamlessly integrate with messaging hubs like Azure IoT Hub and AWS IoT Core or use REST.
To simplify design and enable seamless scaling for large systems, the ScaleOut Digital Twin Streaming Service creates a digital twin for every data source being tracked. A digital twin is a software object that holds contextual information about the data source and application-defined code for analyzing incoming messages. ScaleOut’s service hosts digital twins in memory and automatically distributes them across a cluster of servers for fast processing.
For example, ScaleOut's digital twins can track a nationwide trucking fleet, which might have tens of thousands of vehicles on the road. Each digital twin stores specific contextual information about a vehicle, such as the intended route, the driver’s profile, maintenance history and cargo parameters. Analytics code can use algorithms or machine learning to continuously assess incoming telemetry with predictive analytics. Digital twins can then alert dispatchers or drivers when they detect issues, such as a lost or erratic driver or an impending maintenance issue. In addition, ScaleOut’s aggregate analytics can roll up dynamic statistics for all digital twins to boost situational awareness of the fleet’s condition.
Many costly train derailments could potentially be prevented using a combination of existing infrastructure and new real-time digital twin technology. In this video, you’ll learn how real-time digital twins can revolutionize accident prevention for railroads by monitoring live data and taking action before derailments occur.