Multi-Agent Reinforcement Learning for Power Grid Topology Optimization

Erica van der Sar, Alessandro Zocca, Sandjai Bhulai
10/4/2023
cs.LGcs.AIeess.SY

No official code found. Best implementation: AngelGiI/ResponsibleMARL (9 stars, last commit 2025-01-23).

Abstract

Recent challenges in operating power networks arise from increasing energy demands and unpredictable renewable sources like wind and solar. While reinforcement learning (RL) shows promise in managing these networks, through topological actions like bus and line switching, efficiently handling large action spaces as networks grow is crucial. This paper presents a hierarchical multi-agent reinforcement learning (MARL) framework tailored for these expansive action spaces, leveraging the power grid's inherent hierarchical nature. Experimental results indicate the MARL framework's competitive performance with single-agent RL methods. We also compare different RL algorithms for lower-level agents alongside different policies for higher-order agents.

View on arXivView PDF

Code Implementations(1)

AngelGiI/ResponsibleMARLCommunity65%

The code in this repository is used for research on the definition of Responsability Areas (RA) in multi-agent reinforcement learning for power grids. This work is an extension of Erica van der Sar's paper "Multi-Agent Reinforcement Learning for Power Grid Topology Optimization" (https://doi.org/10.48550/arXiv.2310.02605).

92Shell, PythonApr 17, 20241 years ago

Similar Papers

Managing power grids through topology actions: A comparative study between advanced rule-based and reinforcement learning agents

90% match1 repo132023

Multi-Agent Reinforcement Learning for Energy Networks: Computational Challenges, Progress and Open Problems

89% match2024

A Scalable Network-Aware Multi-Agent Reinforcement Learning Framework for Decentralized Inverter-based Voltage Control

89% match2023

Hierarchical Reinforcement Learning for Power Network Topology Control

89% match1 repo122023

HUGO -- Highlighting Unseen Grid Options: Combining Deep Reinforcement Learning with a Heuristic Target Topology Approach

87% match2024

Power Grid Control with Graph-Based Distributed Reinforcement Learning

87% match2025

Cite this paper

@article{sar2023multiagent,
  title  = {Multi-Agent Reinforcement Learning for Power Grid Topology Optimization},
  author = {Erica van der Sar and Alessandro Zocca and Sandjai Bhulai},
  year   = {2023},
  eprint = {2310.02605},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2310.02605v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2310.02605.svg)](https://codeofpaper.com/paper/2310.02605)

Discussion