Electrical digital twins empower utilities to optimize grid performance by providing a unified data repository, ensuring seamless automated data exchange between internal and external systems.
Demand for electrical power is climbing sky-high, thanks in large part to a seemingly unsatiable demand for compute power for artificial intelligence and related technologies. Microsoft recently sealed a deal to restart the Three Mile Island nuclear plant for this very purpose, and Amazon and Google announced intentions to power their data centers with small modular reactors.
“Nuclear power will be a key part of a suite of new energy infrastructure built to meet surging data-center power demand driven by artificial intelligence,” a recent report out of Goldman Sachs relates. “Electricity usage by data centers is expected to more than double by 2030. In total, 85-90 gigawatts of new nuclear capacity would be needed to meet all of the data center power demand growth expected by 2030.”
AI and digital technologies may be usurping a great deal of electricity, but will also help manage the flow of power as well. The industry is turning to digital twins to monitor and maintain capacity, and there are even emerging projects to build digital twins for nuclear reactors themselves.
See also: Generative AI Helps Build Digital Twins, Digital Twins Help Support AI
Enter Electrical Digital Twins
The electrical digital twins market, valued at $1.2 billion as of 2023, is expected to grow at a rate of five percent a year, reaching $1.73 billion by 2032, a recent market report estimates. “An electrical digital twin serves as an integrated engineering and real-time platform that boosts productivity, enhances efficiency, and facilitates the digital transformation of power systems across all phases of their lifecycle-from initial design and construction to ongoing operation and maintenance,” the report’s authors explain.
Electrical digital twins “empower utilities to optimize grid performance by providing a unified data repository, ensuring seamless automated data exchange between internal and external systems. They enhance operational efficiency by predicting equipment performance, optimizing maintenance schedules, and minimizing downtime. As utilities and industrial sectors increasingly adopt smart grid technologies and renewable energy sources, the demand for electrical digital twins is rising to ensure grid reliability, improve asset management, and support sustainable energy initiatives.”
At the nuclear reactor level, at least two universities are piloting digital twins intended to monitor reactors for anomalies. Idaho State University, for one, has been developing a digital twin to detect off-normal operations with its experimental reactor, as explained in a recent report in the Annals of Nuclear Energy. The digital twin combines machine learning, reactor physics, and visualization within a digital warehouse to create a digital twin. The goal of the project is to serve as a “test bed for developing a digital twin to realize remote monitoring for nuclear reactors. The goal is to monitor the reactor and detect when undeclared events take place to provide information for a monitoring agency.”
At Purdue University, “the nation’s first licensed fully-digitalized nuclear research reactor is providing real-time operational data from the reactor instrumentation system,” writes Purdue Assistant Professor Stylianos Chatzidakis, PhD, in Medium. “We envision that digital-twin technologies will become more standard and accessible as we look forward to the great advancements of the nuclear industry.”
The Purdue University research reactor serves as test bed for optimizing performance of small modular reactors, Chatzidakis added. “To expand the availability of electricity generated from nuclear power, several countries have started developing designs for small modular reactors, which could take less time and money to construct compared to existing reactors.’
A challenge with existing reactors is they are equipped with analog systems, “limiting how much AI can benefit their operation,” he explained. These reactors require digital instrumentation and control systems for the twinning tools. “SMRs, on the other hand, will have digital gauges and sensors, opening a door for AI to collect real-time data and inform their design and performance more comprehensively.”
The Purdue reactor is the site of the first digital twin nuclear reactor control system on a university campus. “The digital twin is a clone that allows researchers to collect real-time data and realistically simulate the reactor on a computer and experiment without affecting the reactor’s operation,” according to a related report out of Purdue. “The data is available in real time through a virtual program, which can then be used to view and analyze the data.”
“With a digital twin, it’s possible to develop the capability to monitor a reactor remotely. In the future, SMRs could use digital twins to have algorithms running in the background that can predict what’s going to happen in the next minute, in the next hour, and then provide information to the operator to make adjustments,” said Chatzidakis.
