Solving Unit Commitment Problems with Graph Neural Network based Initial Commitment Prediction and Large Neighborhood Search

TL;DR

This paper introduces a novel framework combining graph neural networks and large neighborhood search to efficiently solve large-scale unit commitment problems in power systems, significantly outperforming traditional methods.

Contribution

It presents a new GNN-based approach for initial commitment prediction and neighborhood search, improving solution quality and computational efficiency for large UCP instances.

Findings

GNN policies outperform commercial solvers on 1080-unit systems.

The framework achieves higher quality solutions faster.

LNS surpasses commercial solvers on complex instances.

Abstract

Unit commitment problem (UCP) is a critical component of power market decision-making. However, its computational complexity necessitates effi-cient solution methods. In this work we propose a framework to accelerate the solving process of the UCP, and the data collecting process for two dis-tinct graph neural network (GNN) policy. We at first train a Neural Initial Commitment Prediction policy to obtain an initial commitment for UCP. Sec-ond, a heuristic process is introduced to restore the feasibility of the initial commitment. Third, get the neighborhood based on the initial prediction then neighborhood search to improve the commitment. At last, we train a Neural neighborhood Prediction policy to predict the neighborhood of the incum-bent commitment at each iteration, continuously optimizing the commitment until the stopping condition is met. This approach produces high-quality ini-tial commitments that can be iteratively refined to meet higher accuracy re-quirements. The experimental results show that the GNN policies trained on the 80-unit system outperform commercial solvers on a 1080-unit system, and LNS performs better than commercial solver on more complex instanc-es.