Learning to Solve the AC Optimal Power Flow via a Lagrangian Approach

TL;DR

This paper introduces a Lagrangian-based neural network approach to solve AC optimal power flow problems, effectively finding globally optimal solutions despite training data containing suboptimal solutions.

Contribution

The paper proposes a novel dual-variable learning method combined with a partial Lagrangian approach to improve ACOPF solution quality.

Findings

Achieves globally optimal solutions on IEEE test networks

Handles suboptimal training data effectively

Uses neural networks for dual variables and partial Lagrangian solutions

Abstract

Using deep neural networks to predict the solutions of AC optimal power flow (ACOPF) problems has been an active direction of research. However, because the ACOPF is nonconvex, it is difficult to construct a good data set that contains mostly globally optimal solutions. To overcome the challenge that the training data may contain suboptimal solutions, we propose a Lagrangian-based approach. First, we use a neural network to learn the dual variables of the ACOPF problem. Then we use a second neural network to predict solutions of the partial Lagrangian from the predicted dual variables. Since the partial Lagrangian has a much better optimization landscape, we use the predicted solutions from the neural network as a warm start for the ACOPF problem. Using standard and modified IEEE 22-bus, 39-bus, and 118-bus networks, we show that our approach is able to obtain the globally optimal cost even when the training data is mostly comprised of suboptimal solutions.