mlsanityData to 14 Oct 2026

Robust Defense Against Extreme Grid Events Using Dual-Policy Reinforcement Learning Agents

arXiv 2411.11180 ↗First posted 17 Nov 2024eess.SY cs.LG cs.SYcited by 0

On the map: Deep reinforcement learning methods → RL for energy, networks and operations

Abstract (arXiv)

Reinforcement learning (RL) agents are powerful tools for managing power grids. They use large amounts of data to inform their actions and receive rewards or penalties as feedback to learn favorable responses for the system. Once trained, these agents can efficiently make decisions that would be too computationally complex for a human operator. This ability is especially valuable in decarbonizing power networks, where the demand for RL agents is increasing. These agents are well suited to control grid actions since the action space is constantly growing due to uncertainties in renewable generation, microgrid integration, and cybersecurity threats. To assess the efficacy of RL agents in response to an adverse grid event, we use the Grid2Op platform for agent training. We employ a proximal policy optimization (PPO) algorithm in conjunction with graph neural networks (GNNs). By simulating agents' responses to grid events, we assess their performance in avoiding grid failure for as long as possible. The performance of an agent is expressed concisely through its reward function, which helps the agent learn the most optimal ways to reconfigure a grid's topology amidst certain events. To model multi-actor scenarios that threaten modern power networks, particularly those resulting from cyberattacks, we integrate an opponent that acts iteratively against a given agent. This interplay between the RL agent and opponent is utilized in N-k contingency screening, providing a novel alternative to the traditional security assessment.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in RL for energy, networks and operations, one of 15 directions in Deep reinforcement learning methods. Builds on 9 of its 27 references that are in the map. First posted on arXiv 17 Nov 2024.

Builds on

9 of 27 references.

References · 9

  1. 2017Proximal Policy Optimization Algorithmscited by 15,215
  2. 2019Fast Graph Representation Learning with PyTorch Geometriccited by 2,434
  3. 2017pandapower - an Open Source Python Tool for Convenient Modeling, Analysis and Optimization of Electric Power Systemscited by 85
  4. 2021Learning to run a Power Network Challenge: a Retrospective Analysiscited by 55
  5. 2021PowerGridworld: A Framework for Multi-Agent Reinforcement Learning in Power Systemscited by 16
  6. 2023Managing power grids through topology actions: A comparative study between advanced rule-based and reinforcement learning agentscited by 16
  7. 2021Curriculum Based Reinforcement Learning of Grid Topology Controllers to Prevent Thermal Cascadingcited by 8
  8. 2022Proximal Policy Optimization with Graph Neural Networks for Optimal Power Flowcited by 4
  9. 2022Curriculum-based Reinforcement Learning for Distribution System Critical Load Restorationcited by 3

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025RL2Grid: Benchmarking Reinforcement Learning in Power Grid Operations
  2. 2025Optimizing Power Grid Topologies with Reinforcement Learning: A Survey of Methods and Challenges
  3. 2024State and Action Factorization in Power Grids
  4. 2026Interpretable Policy Distillation for Power Grid Topology Control
  5. 2024HUGO -- Highlighting Unseen Grid Options: Combining Deep Reinforcement Learning with a Heuristic Target Topology Approach
  6. 2024A Review of Safe Reinforcement Learning Methods for Modern Power Systems
  7. 2024Graph Reinforcement Learning for Power Grids: A Comprehensive Survey
  8. 2025Graph-Enhanced Model-Free Reinforcement Learning Agents for Efficient Power Grid Topological Control