Offline Reinforcement Learning for Microgrid Voltage Regulation
This addresses voltage regulation in microgrids for energy systems where online interaction is unsafe or impractical, but it appears incremental as it applies existing offline RL methods to this domain.
This paper tackles the problem of microgrid voltage regulation with solar power penetration by using offline reinforcement learning algorithms, demonstrating feasibility and effectiveness on the IEEE 33-bus system with different datasets including low-quality experience.
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.