PV Under Battery Charging Application with MPPT Technique Using HCO–LRNN Approach

The development of quick and accurate Maximum Power Point Tracking (MPPT) for a range of Photovoltaic (PV) applications is the focus of current research. However, the use of traditional MPPT methods and their analysis methodologies is essentially limited by the limitations imposed by size, cost, efficiency and tracking performance. This paper proposes an innovative technique for tracking the Maximum Power Point (MPP) of the battery charging systems under Partial Shading Conditions (PSC). The proposed novel approach combines the Hermit Crab Optimization (HCO) and Local Randomized Neural Networks (LRNN), which is termed the HCO–LRNN technique. The major objective of the proposed approach is to maximize the PV power, enhance tracking efficiency and increase the overall performance of the system. The HCO technique is used to track the Global Maximum Power Point (GMPP) of a battery charging system. The LRNN approach is utilized to predict the current State of Charge (SoC) of the battery under various load conditions. The proposed technique is assessed and compared to other existing methods using the MATLAB platform. The proposed technique outperforms any existing methods, including Harris Hawks Optimization (HHO), Ant Lion Optimization (ALO) and Particle Swarm Optimization (PSO). The proposed method achieves an efficiency of 99.99% and a rapid tracking speed of 0.28[Formula: see text]s. These results confirm the HCO–LRNN approach as a highly effective solution, delivering significant improvements in the reliability and performance of PV battery charging applications under complex, shading environments.