Automated Heuristic Design for Unit Commitment Using Large Language Models

2025-06-14

AI Summary

Unit commitment (UC) in power systems has long suffered from heuristic design relying heavily on manual effort, with limited generalizability and robustness. This paper pioneers the integration of large language models (LLMs) into UC heuristic synthesis, proposing an automated strategy evolution framework grounded in function-space search (FunSearch). The framework leverages LLM-driven program synthesis to generate candidate heuristics, which are iteratively refined via a Lagrangian relaxation–based optimization loop coupled with a verifiable simulation-based evaluator. This closed-loop evolutionary process ensures interpretability, full automation, and strong robustness. Evaluated on a standard 10-unit test system, the method significantly reduces sampling and evaluation time compared to genetic algorithms while lowering total system operating cost. These results demonstrate both computational efficiency and practical engineering viability.

Technology Category

• Search and Optimization: Heuristic Search
• Reasoning under Uncertainty: Stochastic Optimization
• Planning, Routing, and Scheduling: Planning with Language Models

Application Category

• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

The Unit Commitment (UC) problem is a classic challenge in the optimal scheduling of power systems. Years of research and practice have shown that formulating reasonable unit commitment plans can significantly improve the economic efficiency of power systems' operations. In recent years, with the introduction of technologies such as machine learning and the Lagrangian relaxation method, the solution methods for the UC problem have become increasingly diversified, but still face challenges in terms of accuracy and robustness. This paper proposes a Function Space Search (FunSearch) method based on large language models. This method combines pre-trained large language models and evaluators to creatively generate solutions through the program search and evolution process while ensuring their rationality. In simulation experiments, a case of unit commitment with (10) units is used mainly. Compared to the genetic algorithm, the results show that FunSearch performs better in terms of sampling time, evaluation time, and total operating cost of the system, demonstrating its great potential as an effective tool for solving the UC problem.

Problem

• Optimizing power system scheduling via Unit Commitment
• Improving UC solution accuracy and robustness
• Reducing operating costs with LLM-based FunSearch

Innovation

• Uses large language models for heuristic design
• Combines pre-trained models with evaluators
• Improves efficiency in power system scheduling