Global Performance Guarantees for Neural Network Models of AC Power Flow

arXiv:2211.07125v3 Announce Type: replace-cross
Abstract: Machine learning, which can generate extremely fast and highly accurate black-box surrogate models, is increasingly being applied to a variety of AC power flow problems. Rigorously verifying the accuracy of the resulting black-box models, however, is computationally challenging. This paper develops a tractable neural network verification procedure which incorporates the ground truth of the non-linear AC power flow equations to determine worst-case neural network prediction error. Our approach, termed Sequential Targeted Tightening (STT), leverages a …

abstract accuracy arxiv box cs.lg cs.sy eess.sy flow generate global however machine machine learning network neural network paper performance power tractable type