Power Flow Feasibility Assessment Using Variational Graph Autoencoders

Researchers developed a Variational Graph Autoencoder (VGAE) to assess power flow solution feasibility in electrical grids, testing it on the IEEE 118-bus system. The model detects whether solutions from AI-driven solvers are valid, addressing a gap in data-driven power flow methods.

Power Flow Feasibility Assessment Using Variational Graph Autoencoders By Ferran Bohigas-Daranas, Hamid Latif-Martinez, Eduardo Prieto-Araujo, Pere Barlet-Ros, Oriol Gomis-BellmuntSource: arXiv cs.LG https://arxiv.org/list/cs.LG/recent arXiv:2607.09122v1 Announce Type: new Abstract: Data-driven methods, including graph neural networks, have been studied for accelerating power flow calculations in recent years, but very little attention /glossary/attention has been paid to the solution feasibility, which can be obtained by traditional solvers. This paper presents a Variational Graph Autoencoder /glossary/autoencoder VGAE that detects the power flow solution feasibility, using the IEEE 118-bus case, to assess the validity of the solutions provided by AI-driven solvers.Get AI news in your inbox Daily digest of what matters in AI.