Deep Reinforcement Learning Based Microgrid Expansion Planning with Battery Degradation and Resilience Enhancement
Kexin Pang, Jian Zhou, Stamatis Tsianikas, Yizhong Ma
Abstract
Nowadays, one of the main goals of long-term microgrid expansion planning is to improve power resilience while minimizing total cost. While the impacts of real-life features of storage units and power generation units are not explored in current literature, this paper establishes a microgrid expansion planning model which takes into account real-world battery degradation mechanism. Reinforcement learning based simulation methods are applied to obtain the optimal microgrid expansion policy. Case studies are conducted to verify the effectiveness of the proposed model and investigate the impact of battery degradation. Furthermore, the influence of the unavailability of power plants during extreme power outages on optimal microgrid expansion planning is also explored.