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

2024/04/24 by Sarah Keren, Keren, Sarah, Chaimaa Essayeh +4
Engineering · #Artificial Intelligence (cs.AI) #FOS: Computer and information sciences #Smart Grid Energy Management #Smart Grid Security and Resilience

paper · pdf · doi:10.48550/arxiv.2404.15583

openalex publication_date 2024/04/24 · openalex created_date 2024/04/26 · openalex updated_date 2026/07/28

Abstract

The rapidly changing architecture and functionality of electrical networks and the increasing penetration of renewable and distributed energy resources have resulted in various technological and managerial challenges. These have rendered traditional centralized energy-market paradigms insufficient due to their inability to support the dynamic and evolving nature of the network. This survey explores how multi-agent reinforcement learning (MARL) can support the decentralization and decarbonization of energy networks and mitigate the associated challenges. This is achieved by specifying key computational challenges in managing energy networks, reviewing recent research progress on addressing them, and highlighting open challenges that may be addressed using MARL.

Related

• Centralised rehearsal of decentralised cooperation: Multi-agent reinforcement learning for the scalable coordination of residential energy flexibility
• Multi-Agent Reinforcement Learning for Power Grid Topology Optimization
• Renewable energy integration and microgrid energy trading using\n multi-agent deep reinforcement learning
• Reinforcement Learning for Sustainable Energy: A Survey
• Multi-Agent Reinforcement Learning for Active Voltage Control on Power Distribution Networks