Artificial Neural Network-Based Inverter Control and MPPT for Enhanced Performance of Hybrid Microgrids With PV and Battery Storage

Today's power system network has become more complex, with greater responsibilities and challenges in providing a secure, reliable, and high-quality energy supply to communities. A smaller entity of the electrical network, known as a Microgrid (MG), has become more popular in recent times to enhance the reliability and security of energy supply during any energy crisis in the utility network. Microgrids (MG) can provide clean energy through renewable resources such as photovoltaic (PV) systems, wind, and energy storage, offering an effective solution for power supply in both remote and urban residential communities. To ensure the stable operation of a standalone microgrid based on a photovoltaic system, it is essential to implement various mechanisms and control strategies simultaneously for optimal efficiency. This paper introduces a complete model of a hybrid microgrid consisting of a PV source, an Artificial Neural Network (ANN)-based Maximum Power Point Tracking (MPPT) system, a storage unit, a DC to AC converter with an ANN controller, and both DC and AC loads. The performance of the controller under various ambient conditions and load variations is tested. The ANN controller demonstrates good performance in different situations.