Neuro-Reachability of Networked Microgrids

A neural ordinary differential equations network (ODE-Net)-enabled reachability method ( Neuro-Reachability ) is devised for the dynamic verification of networked microgrids (NMs) with unidentified subsystems and heterogeneous uncertainties. Three new contributions are presented: 1) An ODE-Net-enabled model discovery approach to construct data-driven state-space which preserves nonlinear structure NMs system; 2) physics-data-integrated (PDI) established, empowers various NM analytics; 3) conformance-empowered analysis developed enhance reliability PDI-driven verification. Extensive case studies demonstrate efficacy in microgrid discovery, effectiveness verifying dynamics under multiple uncertainties operational scenarios.