Conference Paper
Proceedings of SimBuild Conference 2024
Reinforcement Learning to Enhance Optimal Operation of Resilient Community Energy Systems
Reinforcement Learning to Enhance Optimal Operation of Resilient Community Energy Systems
Zhuorui Li 1, Xu Han 1, Jing Wang 2, Wangda Zuo 31 The University of Kansas 2 National Renewable Energy Laboratory 3 The Pennsylvania State UniversityAbstract: This paper presents a novel model-free multi-agent Reinforcement Learning (RL) control method to enhance the resilience of community energy systems in island mode, which coordinates multiple objectives without the necessity of identifying system models that require expert knowledge. Specifically, a community-level coordinator agent is designed to allocate renewable energy resources among different buildings, and multiple building-level agents are developed to optimize load schedules based on limited energy resources and requirements of building loads and occupants’ comfort. In a two-day evaluation, our RL approach demonstrated a similar performance against MPC without requiring system models and formulation of optimization problems as required in MPC. Keywords: resilient community, reinforcement learning, PV power distributionPages: 668 - 678 Paper: