A Comprehensive Comparative Study and Optimization of MPPT Algorithms in a Standalone Photovoltaic Plant using Classical and Machine Learning Techniques

In recent years, various control methods for the Maximum Power Point Tracker (MPPT) of Photovoltaic (PV) systems have been proposed and evaluated in terms of energy efficiency, power conversion, dynamic performance, and reliability under different environmental conditions. Among these methods, those based on Artificial Intelligence (AI) are considered the best due to their stability and lack of requirement for prior information on the physical parameters. In this paper, a comparison between two PV systems using classical MPPT algorithms and Machine Learning (ML) algorithms has been conducted. This study introduces a novel angle to photovoltaic systems by conducting a comprehensive comparative analysis of Maximum Power Point Tracker (MPPT) algorithms. It innovatively contrasts classical techniques with emerging Machine Learning (ML) methods, rigorously evaluating them across energy efficiency, power conversion, and dynamic performance parameters. Through MATLAB/Simulink simulations, it demonstrates the superior performance of MLbased MPPT methods in stability, speed, and efficiency.