Self-Supervised Graph Neural Networks for Optimal Substation Reconfiguration

TL;DR

This paper introduces a self-supervised graph neural network approach to optimize substation reconfiguration, achieving near-MILP performance with significantly faster computation times.

Contribution

It presents a novel GNN-based method for OSR framed as an amortized optimization problem, enabling real-time decision-making with competitive results.

Findings

GNN model improves exchange capacity by 10.2% on average.

Classical MILP achieves 15.2% improvement but with much higher computation times.

Proposed approach is suitable for real-time substation reconfiguration.

Abstract

Changing the transmission system topology is an efficient and costless lever to reduce congestion or increase exchange capacities. The problem of finding the optimal switch states within substations is called Optimal Substation Reconfiguration (OSR), and may be framed as a Mixed Integer Linear Program (MILP). Current state-of-the-art optimization techniques come with prohibitive computing times, making them impractical for real-time decision-making. Meanwhile, deep learning offers a promising perspective with drastically smaller computing times, at the price of an expensive training phase and the absence of optimality guarantees. In this work, we frame OSR as an Amortized Optimization problem, where a Graph Neural Network (GNN) model -- our data being graphs -- is trained in a self-supervised way to improve the objective function. We apply our approach to the maximization of the exchange capacity between two areas of a small-scale 12-substations system. Once trained, our GNN model improves the exchange capacity by 10.2% on average compared to the all connected configuration, while a classical MILP solver reaches an average improvement of 15.2% with orders-of-magnitude larger computing times.