BMS for Wind-Solar Hybrid System with Predictive Control Strategies

Abstract: The increasing penetration of renewable energy sources into power systems introduces challenges related to intermittency, load uncertainty, and grid stability. This project proposes an Artificial Neural Network (ANN)-based Energy Management System (EMS) for a wind–solar hybrid microgrid (though the presented work focuses on PV, the framework is extensible) with predictive control strategies to address these issues. The system comprises two interconnected microgrids, each featuring photovoltaic (PV) generation, a battery energy storage system (BESS), local loads, and power electronic converters. A key innovation is the integration of an ANN controller that predicts load demand and energy requirements with high accuracy (~99%) by learning from historical data. Based on these predictions, the EMS dynamically balances generation, storage, and demand, deciding in real time whether to charge the battery from surplus PV or discharge during deficits. A Multi-Microgrid Controller (MMGC) further enables efficient power sharing between the two microgrids, enhancing overall reliability and energy utilization. The proposed approach improves grid stability, reduces energy wastage and power imbalance, and ensures uninterrupted power supply despite renewable fluctuations. Validated through literature-supported methodologies, this ANN-based predictive EMS offers a scalable, intelligent solution for modern renewable-integrated microgrids, contributing to enhanced energy efficiency, reduced operational costs, and resilient multi-microgrid operation.

Keywords: BMS, ANN, PV. EMS, Multi-Microgrid Controller, a battery energy storage system (BESS)