Digital twins have historically been employed as a tool for modeling the detailed behavior of a complex physical entity, like a jet engine. The ScaleOut Digital Twins service now enables digital twins to implement simulation models of large systems. Its highly scalable, in-memory computing architecture enables digital twins to model many thousands of entities and their interactions in a time-driven simulation. This provides a powerful new tool for extracting insights and making predictions that today’s operational managers need to make key decisions, enabling their systems to operate at peak efficiency.
For example, an airline can create a simulation of its passengers, aircraft, airport gates, and other entities to assess the impact of weather delays and other outages (such as ground stops). Simulations like this help managers model live scenarios, identify problems, and make decisions, such as to dynamically change airline schedules.
ScaleOut Digital Twins can optionally record incoming messages, save them to a database, and then play them back in simulation. This feature lets developers repeatedly subject streaming analytics code to an actual workload.
You can vary the speed that a simulation runs relative to real time. For example, simulations can run at the same speed as real time to help demonstrate and visualize evolving behavior. They can run faster than real time to deliver predictions as quickly as possible.
You can take full advantage of ScaleOut's built-in aggregate analytics to capture and visualize trends while a simulation is running. You can also query the state of individual digital twins and create a geospatial mapping that refreshes continuously.
ScaleOut’s digital twins integrates simulation with real-time analytics to implement several compelling use cases. Simulations can run alongside real-time digital twins to provide predictive modeling that helps steer the behavior of a live system. For example, an airline simulation can make use of live data to evaluate the benefits of dynamic changes to flight schedules during live operations.
Digital twin simulations also can create workloads to test real-time analytics prior to deployment in a live system. For example, digital twins can validate streaming analytics for a telematics application that tracks a fleet of trucks. Each digital twin generates periodic messages that correspond to telemetry emitted by a single truck; a corresponding real-time digital twin consumes the messages to look for issues that need attention. This technique enables testing of a wide range of scenarios that might be encountered during actual operations.