Large Language Models for Solving Economic Dispatch Problem

TL;DR

This paper explores using large language models with reasoning capabilities to solve the economic dispatch problem efficiently without traditional mathematical formulations or extensive training.

Contribution

It introduces a novel approach leveraging LLMs with few-shot prompting to address the classic ED problem, bypassing common challenges of existing methods.

Findings

LLMs can effectively solve the ED problem with appropriate prompting.

The approach avoids convergence issues typical of traditional optimization methods.

It requires no labeled data or extensive training, offering a practical alternative.

Abstract

This paper investigates the capability of off-the-shelf large language models (LLMs) to solve the economic dispatch (ED) problem. ED is a hard-constrained optimization problem solved on a day-ahead timescale by grid operators to minimize electricity generation costs while accounting for physical and engineering constraints. Numerous approaches have been proposed, but these typically require either mathematical formulations, face convergence issues, or depend on extensive labeled data and training time. This work implements LLMs enhanced with reasoning capabilities to address the classic lossless ED problem. The proposed approach avoids the need for explicit mathematical formulations, does not suffer from convergence challenges, and requires neither labeled data nor extensive training. A few-shot learning technique is utilized in two different prompting contexts. The IEEE 118-bus system with 19 generation units serves as the evaluation benchmark. Results demonstrate that various prompting strategies enable LLMs to effectively solve the ED problem, offering a convenient and efficient alternative. Consequently, this approach presents a promising future solution for ED tasks, particularly when foundational power system models are available.