Deep reinforcement learning for resilient microgrid expansion planning with multiple energy resource
Kexin Pang, Jian Zhou, Stamatis Tsianikas, Yizhong Ma
Abstract
Abstract Microgrid has attracted more and more attention to provide backup power for customers in the case of power grid outages. Microgrid expansion planning is significant to handle the increasing customer demand and to enhance power resilience. Current research about long‐term microgrid expansion planning rarely if ever considered the uncertainties associated with energy storage and power generation units, for example, battery cycle degradation. These factors have important influence on the performance of microgrid expansion planning in reality. In this paper, a long‐term microgrid expansion planning model with multiple energy resource is presented. Deep reinforcement learning method is used to obtain the cost‐effective microgrid expansion policies to enhance power resilience. In the case study, optimal microgrid expansion planning is achieved based on the proposed model. The impacts of battery degradation and resilience constraint on microgrid expansion policy optimization are also investigated. The simulation results prove the effectiveness of the proposed method on economic and resilient microgrid expansion planning.