Research map / Multi-agent systems and games / Cooperative multi-agent RL
Multi-Agent Reinforcement Learning for Active Voltage Control on Power Distribution Networks
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Use Bowl-shape instead of L1-shape or L2-shape voltage barriers (ablation) | MARL active voltage control · 33-bus and 141-bus networks | power loss | Mixed |
| Use L1-shape instead of Bowl-shape or L2-shape voltage barriers (ablation) | MARL active voltage control · 33-bus and 141-bus networks | controllable rate | Helped |
| Use L1-shape instead of Bowl-shape or L2-shape voltage barriers (ablation) | MARL active voltage control · 141-bus network | power loss | Hurt |
| Use L2-shape instead of Bowl-shape or L1-shape voltage barriers (ablation) | MARL active voltage control · 33-bus and 141-bus networks | controllable rate | Hurt |
| Use L2-shape instead of Bowl-shape or L1-shape voltage barriers (ablation) | MARL active voltage control · 322-bus network | controllable rate | Helped |
| Use Bowl-shape instead of L1-shape or L2-shape voltage barriers (ablation) | MARL active voltage control · 322-bus network | power loss | Hurt |
| Scale from smaller networks to many agents | COMA · Larger-scale networks | controllable rate | Hurt |
| Scale from smaller networks to many agents | SQDDPG · 322-bus network | controllable rate | Hurt |
| Use MADDPG instead of other evaluated MARL algorithms | MARL active voltage control · 33-bus, 141-bus, and 322-bus networks | overall performance | Helped |
| Use MATD3 instead of other evaluated MARL algorithms | MARL active voltage control · 33-bus, 141-bus, and 322-bus networks | overall performance | Helped |
| Use MARL instead of droop control | MADDPG trained with Bowl-shape · 33-bus network | power loss | Helped |
| Use MARL instead of OPF | MADDPG trained with Bowl-shape · 33-bus network | power loss | Hurt |
Closest papers by meaning
- Benchmarking Multi-Agent Reinforcement Learning in Power Grid Operations (ICLR 2026 · similarity 0.90)
- Multi-Agent Reinforcement Learning for Modeling, Simulating, and Optimizing Energy Markets (AAAI 2026 · similarity 0.88)
- Continuous Multiagent Control Using Collective Behavior Entropy for Large-Scale Home Energy Management (AAAI 2020 · similarity 0.86)
- Winning the L2RPN Challenge: Power Grid Management via Semi-Markov Afterstate Actor-Critic (ICLR 2021 · similarity 0.86)
- WFCRL: A Multi-Agent Reinforcement Learning Benchmark for Wind Farm Control (NeurIPS 2024 · similarity 0.84)
- Finite-Time Global Optimality Convergence in Deep Neural Actor-Critic Methods for Decentralized Multi-Agent Reinforcement Learning (ICML 2025 · similarity 0.82)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.