Power Flow Feasibility Assessment Using Variational Graph Autoencoders
For power system operators using AI-driven solvers, this method assesses solution validity, but it is an incremental application of existing techniques to a known problem.
The paper proposes a Variational Graph Autoencoder (VGAE) to detect power flow solution feasibility, achieving high accuracy on the IEEE 118-bus system, though no specific numbers are provided.
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.