Work

Review on Application and Challenges of Large Language Models in Power Grids

Year: 2025

Type: article

Abstract: Power grids are critical infrastructures that require real-time safe and reliable operation. Large Language Models (LLMs), have demonstrated significant potential in power grid applications. This paper presents a comprehensive review of the applications of LLMs in power grids, covering areas such as intelligent assistance for grid operation, generation and load forecasting, power system planning and operation, and power converter design. Additionally, the paper discusses key challenges associated with the integration of LLMs into power grids, including data quality issues, model explainability, cybersecurity risks, and real-time computational efficiency. Potential solutions are provided to enhance the reliability and applicability of LLMs in power grid applications. By leveraging the capabilities of LLMs, power system operators can enhance decision-making processes, improve operational efficiency, and foster a more resilient and adaptive power infrastructure.

Source: IEEE Access

DOI: 10.1109/access.2025.3580439

Authors: Liudong Zhang, Wenlu Ji, Yulin Zhao, Di Huang, Bingjun Qian

Institutions: State Grid Jiangsu Electric Power (China), State Grid Nanjing Power Supply Company (China)

Language: English

Topic: Smart Grid and Power Systems

Subfield: Electrical and Electronic Engineering

Field: Engineering

Domain: Physical Sciences

SDGs: Affordable and clean energy, Industry, innovation and infrastructure

Open Access status: gold

Estimated APC paid: $2,075