Enhanced MPPT Performance in Solar PV System Using ANN and FOPI Control Optimized by Meta-Heuristic Algorithm

Solar energy stands as one of the most widely harnessed clean, green, and renewable energy sources. With the escalating global demand for electricity, it becomes imperative to optimize energy extraction from such sustainable resources. This study is dedicated to enhancing solar power output through advanced Maximum Power Point Tracking (MPPT) methodologies, leveraging intelligent control strategies. Specifically, it presents a comparative analysis of various MPPT algorithms implemented using Artificial Neural Networks (ANN), integrated with different control schemes. The conventional Proportional-Integral (PI) controller, while commonly used, demonstrates limitations including sluggish dynamic response, inadequate adaptability to varying irradiance conditions, and reduced tracking precision. To address these shortcomings, this research adopts a Fractional Order Proportional-Integral (FOPI) controller, with its parameters optimally tuned using two prominent metaheuristic algorithms: Flower Pollination Algorithm (FPA) and Grey Wolf Optimization (GWO). Simulation results clearly indicate that the FOPI controller significantly outperforms the traditional PI controller, offering superior responsiveness, enhanced tracking accuracy, and more robust performance under dynamic environmental conditions.