The concept of digital twins has become a hot topic over the last few years. Historically, it was employed as a tool for modeling the detailed behavior of a single, complex physical entity, like a jet engine. New technology now enables it to enjoy much broader application in large enterprises to help manage complex operations. Airlines, trucking fleets, logistics hubs, telecommunications networks, security infrastructures, and countless other systems need to efficiently keep track of large populations of assets that help deliver value to enterprise customers while wringing out a high return on investment. These systems inevitably become more complex over time and more challenging to manage. Digital twins can help.
An Important New Role for Digital Twins
As the world has embraced the proliferation of smart IoT devices, enterprise systems have incorporated them to track assets like airline bags, pallets, and vehicles. These devices help keep track of location, condition, and other vital parameters. When used at scale, they generate huge streams of telemetry that typically flow into corporate data lakes and other data warehousing solutions. Operations managers must then mine these databases to find issues that need fixing and opportunities to optimize operations. The problem is that there’s just too much data and too little time to digest it quickly.
Digital twins can break this bottleneck and enable fast, effective action that results in smoother operations and lower costs. Managers can implement continuous monitoring and immediate alerting when problems or opportunities arise by assigning a digital twin to continuously track telemetry from each asset.
For example, a trucking fleet can create a digital twin for each truck to track its location, engine condition, cargo status, driver’s duty time and behavior, and many other dynamic parameters. Each digital twin can combine this telemetry with specific information, such as the truck’s service history and the driver’s recent schedule, to intelligently evaluate whether to alert an operations manager.
What makes digital twins powerful is their ability to quickly evaluate the latest information about an asset in a rich context that helps identify emerging issues. They can incorporate machine learning algorithms to assist them in making this assessment.
Imagine a fleet using thousands of digital twins to track its vehicles. These digital twins give operations managers powerful new capabilities for boosting situational awareness and focusing their attention on the most important problems. Incorporating digital twins into the workflow can drive down costs and help the enterprise deliver the best possible service to its customers.
The Enabling Technology: In-Memory Computing
Simultaneously running thousands of digital twins that can analyze telemetry in milliseconds requires a fast, scalable hosting platform, like the ScaleOut Digital Twin Streaming Service. It uses “in-memory computing” technology to deliver the required computing power. Instead of just storing key information in databases, where it can be slow to retrieve and analyze, in-memory computing keeps all needed data in memory within each digital twin. This technology automatically combines multiple computers or cloud instances into a single, highly scalable cluster. It also routes incoming messages to their corresponding digital twins for processing to avoid unnecessary data motion and delays.
In-memory computing enables thousands (or even millions) of digital twins to continuously process incoming telemetry with peak performance. This is just what enterprise applications need to track large populations of data sources, provide immediate alerting, and visualize emerging trends.
The Next Step: Making Predictions
To keep complex operations running smoothly, it’s not enough just to track assets and look for issues and opportunities as they arise. Enterprises also need to move from a reactive to a proactive posture by making predictions that help steer operational decisions. For example, when weather and equipment delays disrupt an airline’s flight schedule, managers need to quickly decide which outbound flights should be held to accommodate late inbound passengers. The ability to make dynamic predictions that measure the impact of alternative choices can dramatically improve decision-making. It will also lead to smoother, more efficient operations and happier customers.
Digital twins can help here, too. They enable managers to easily build time-driven simulations which model thousands of interacting assets and run faster than real-time. Instead of ingesting and analyzing live telemetry, these digital twins exchange messages that model intricate interactions among assets and calculate quantitative impacts on system behavior. By exploring multiple scenarios and comparing outcomes, digital twin simulations give managers a powerful new predictive tool for optimizing their complex systems.
For example, an airline can use digital twin simulations to model the myriad entities within a large airline system, such as passengers, aircraft, airport gates, and air traffic sectors. Digital twins maintain state information about the physical entities they represent, and they run code and exchange messages at each time step in a simulation’s execution to update their state over time. By modeling weather events and system outages, a simulation can measure the impact of flight delays, evaluate gate congestion, and propose changes to passenger itineraries. Managers can run multiple simulations faster than real time to evaluate alternative scheduling decisions that respond to these situations and assist them in decision-making.
Our world depends on the smooth operation of large and increasingly complex enterprise systems. Managers need to deliver optimal performance while keeping a lid on operational costs. These systems’ complexity and overwhelming volumes of real-time data make extracting timely and actionable insights an immense challenge. Traditional tools for real-time monitoring, such as stream pipelines, database queries and log file analysis, just don’t provide the granular insights and predictions managers require. Gaining these insights requires innovative software technology like digital twins that can simultaneously track, analyze, and model thousands of assets.
The ScaleOut Digital Twin Streaming Service was specifically designed to meet this need. ScaleOut Software has created a breakthrough computing platform for real-time monitoring and decision-making by combining digital twins with scalable, in-memory computing. By simultaneously running thousands of digital twins in memory to track assets and make predictions, operational managers can quickly surface insights that otherwise would be hidden in the daunting complexity of their systems. With these insights, they can boost operational effectiveness to the level that both customers and executive management demand.
Founded in 2003, ScaleOut Software develops leading-edge software that delivers scalable, highly available, in-memory computing and streaming analytics technologies to a wide range of industries. ScaleOut Software’s in-memory computing platform enables operational intelligence by storing, updating, and analyzing fast-changing, live data so that businesses can capture perishable opportunities before the moment is lost.