Nuclear-Renewable-Storage Digital Twin: Enhancing Design, Dispatch, and Cyber Response of Integrated Energy Systems

This project will develop a learning-based and digital twin enabled modeling and simulation framework for economic and resilient real-time decision-making of physics- informed integrated energy systems (IES) operation. High-fidelity physics models will be linked with large-scale grid monitoring data to provide real-time updates of IES states, predictive control systems, and optimized power dispatch solutions. Learning- based algorithms will make real-time decisions upon detection of component contingencies caused by climate-induced or man-made extreme events, such as cyber-attacks or extreme weather, thereby mitigating their impacts through
appropriate counter measures.