Energy Management for Rural Microgrid With Inaccurate Equipment Parameters: A KAN-Based Deep Reinforcement Learning Method

Chenhao Lin, Ying Xu, Zhongkai Yi, Zhenghong Tu

Abstract: During the agricultural season, the proportion of irrigation load in rural microgrid increases rapidly. However, the energy can hardly be managed effectively due to the surge in irrigation load, rapid fluctuations of renewable energy, and inaccurate electrical parameters of aging equipment. In this article, an energy management model for rural microgrid including irrigation, hydrogen, electric heating, and power systems is proposed. Further, formidable challenges arise from inaccurate water-electricity conversion coefficient of water pump and non-convex dynamic efficiency function of hydrogen energy storage system. A deep reinforcement learning (DRL) method is proposed incorporating a Kolmogorov-Arnold network (KAN) structure and a two-stage implementation deployment method, which maintains robustness against discrepancies between the controlled training environment and the dynamic application scenario. The results of simulation experiments demonstrate adaptability and robustness of the KAN-based method in handling deviations of equipment parameters. The effectiveness and superiority of KAN-based DRL approach are validated through a comparative analysis with the state-of-the-art algorithms.

External IDs:dblp:journals/tsg/LinXYT25