Physics-Informed Neural Networks for AC Optimal Power Flow

TL;DR

This paper presents a novel physics-informed neural network approach for solving the AC Optimal Power Flow problem, providing accuracy improvements and rigorous constraint violation guarantees in power system optimization.

Contribution

It introduces the integration of AC power flow equations into neural network training and methods to rigorously bound constraint violations, advancing ML applications in power systems.

Findings

Higher accuracy than standard neural networks

Lower constraint violations achieved

Reduced worst-case violations across input domain

Abstract

This paper introduces, for the first time to our knowledge, physics-informed neural networks to accurately estimate the AC-OPF result and delivers rigorous guarantees about their performance. Power system operators, along with several other actors, are increasingly using Optimal Power Flow (OPF) algorithms for a wide number of applications, including planning and real-time operations. However, in its original form, the AC Optimal Power Flow problem is often challenging to solve as it is non-linear and non-convex. Besides the large number of approximations and relaxations, recent efforts have also been focusing on Machine Learning approaches, especially neural networks. So far, however, these approaches have only partially considered the wide number of physical models available during training. And, more importantly, they have offered no guarantees about potential constraint violations of their output. Our approach (i) introduces the AC power flow equations inside neural network training and (ii) integrates methods that rigorously determine and reduce the worst-case constraint violations across the entire input domain, while maintaining the optimality of the prediction. We demonstrate how physics-informed neural networks achieve higher accuracy and lower constraint violations than standard neural networks, and show how we can further reduce the worst-case violations for all neural networks.