Renewable-integrated hybrid microgrid energy management using the BEO-DPCNN framework

Hybrid microgrid (MG) energy management (EM) integrating renewable generation and energy storage is essential for ensuring a reliable, economical, and sustainable power supply under variable generation and demand conditions. This study presents a hybrid Black Eagle Optimization-Deep Pulse Coupled Neural Network (BEO-DPCNN) framework for intelligent EM in a hybrid MG comprising photovoltaic (PV), wind turbines (WTs), battery energy storage (BES), grid interaction, and variable load profiles. In the proposed framework, the DPCNN forecasts renewable generation and load variations, while the BEO algorithm optimally schedules energy dispatch to minimize operating cost, CO 2 emissions, and average power losses while maximizing overall system performance. The proposed method is evaluated under varying generation and demand conditions in a renewable-integrated hybrid MG and compared with recent EM approaches, including FFO-DADRCNN, ARONN, MCCHGNN-IBESOA, ANN, and IAGA. This simulation shows that the proposed framework consistently leads to better economic, environmental and operational results by optimizing the coordination between renewable resources, battery storage (BS) and power exchange with the grid. These results confirm that the proposed BEO-DPCNN technique provides a reliable and efficient solution for intelligent hybrid MG EM.