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

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Yang, Linfeng, Li, Peilun, Jian, Jinbao
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866915295138938880
author Yang, Linfeng
Li, Peilun
Jian, Jinbao
author_facet Yang, Linfeng
Li, Peilun
Jian, Jinbao
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2505_14408
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Solving Unit Commitment Problems with Graph Neural Network based Initial Commitment Prediction and Large Neighborhood Search
Yang, Linfeng
Li, Peilun
Jian, Jinbao
Optimization and Control
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.
title Solving Unit Commitment Problems with Graph Neural Network based Initial Commitment Prediction and Large Neighborhood Search
topic Optimization and Control
url https://arxiv.org/abs/2505.14408