RT26 Edinburgh | Physics-informed datadriven digital twin surrogates

This presentation explores physics-informed, data-driven digital twin surrogates for real-time control, planning, and decision support in modern Power Systems. Drawing on Durham University’s Smart Grid Lab and OPAL-RT platforms, including the OP5707XG and OP5033XG, it presents resilient distributed and decentralized control strategies for converter-connected Microgrid applications, alongside AI/ML-assisted models for rapid system optimization and validation. The work connects real-time simulation with broader operational challenges such as renewable integration, frequency stability, uncertainty management, and long-term Transmission investment planning, demonstrating how high-fidelity models and surrogate digital twins can support faster, more reliable, and computationally efficient decisions.