Power Flow Feasibility Assessment Using Variational Graph Autoencoders
Machine Learning
2026-07-10 v1 Systems and Control
Abstract
Data-driven methods, including graph neural networks, have been studied for accelerating power flow calculations in recent years, but very little attention has been paid to the solution feasibility, which can be obtained by traditional solvers. This paper presents a Variational Graph 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.
Cite
@article{arxiv.2607.09122,
title = {Power Flow Feasibility Assessment Using Variational Graph Autoencoders},
author = {Ferran Bohigas-Daranas and Hamid Latif-Martinez and Eduardo Prieto-Araujo and Pere Barlet-Ros and Oriol Gomis-Bellmunt},
journal= {arXiv preprint arXiv:2607.09122},
year = {2026}
}
Comments
Conference