English

Reinforcement Learning Optimizes Power Dispatch in Decentralized Power Grid

Physics and Society 2024-07-30 v1 Systems and Control Systems and Control Adaptation and Self-Organizing Systems

Abstract

Effective frequency control in power grids has become increasingly important with the increasing demand for renewable energy sources. Here, we propose a novel strategy for resolving this challenge using graph convolutional proximal policy optimization (GC-PPO). The GC-PPO method can optimally determine how much power individual buses dispatch to reduce frequency fluctuations across a power grid. We demonstrate its efficacy in controlling disturbances by applying the GC-PPO to the power grid of the UK. The performance of GC-PPO is outstanding compared to the classical methods. This result highlights the promising role of GC-PPO in enhancing the stability and reliability of power systems by switching lines or decentralizing grid topology.

Keywords

Cite

@article{arxiv.2407.15165,
  title  = {Reinforcement Learning Optimizes Power Dispatch in Decentralized Power Grid},
  author = {Yongsun Lee and Hoyun Choi and Laurent Pagnier and Cook Hyun Kim and Jongshin Lee and Bukyoung Jhun and Heetae Kim and Juergen Kurths and B. Kahng},
  journal= {arXiv preprint arXiv:2407.15165},
  year   = {2024}
}

Comments

11 pages, 6 figures

R2 v1 2026-06-28T17:48:45.955Z