Offline Reinforcement Learning for Microgrid Voltage Regulation

2025/05/15 by Shan Yang, Yang, Shan, Yongli Zhu +1
Engineering · #Artificial Intelligence (cs.AI) #FOS: Computer and information sciences #FOS: Electrical engineering #Microgrid Control and Optimization #Optimal Power Flow Distribution #Smart Grid Energy Management #Systems and Control (eess.SY) #electronic engineering #information engineering

paper · pdf · doi:10.48550/arxiv.2505.09920

openalex publication_date 2025/05/15 · openalex created_date 2025/10/15 · openalex updated_date 2026/07/28

Abstract

This paper presents a study on using different offline reinforcement learning algorithms for microgrid voltage regulation with solar power penetration. When environment interaction is unviable due to technical or safety reasons, the proposed approach can still obtain an applicable model through offline-style training on a previously collected dataset, lowering the negative impact of lacking online environment interactions. Experiment results on the IEEE 33-bus system demonstrate the feasibility and effectiveness of the proposed approach on different offline datasets, including the one with merely low-quality experience.

Citations

• On the Opportunities and Challenges of Offline Reinforcement Learning for Recommender Systems
• Learning to Control Autonomous Fleets from Observation via Offline Reinforcement Learning
• Multi-Agent Reinforcement Learning for Active Voltage Control on Power Distribution Networks
• Conservative Q-Learning for Offline Reinforcement Learning
• Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems
• Off-Policy Deep Reinforcement Learning without Exploration

Related

• Embedded Machine Learning for Solar PV Power Regulation in a Remote Microgrid
• Safe Reinforcement Learning for Power System Control: A Review
• Coordination of PV Smart Inverters Using Deep Reinforcement Learning for Grid Voltage Regulation
• Multi-Agent Reinforcement Learning for Active Voltage Control on Power Distribution Networks
• Reinforcement Learning\unicodex2013Based Transient Response Shaping for Microgrids