improving the efficiency of photovoltaic cell system using artificial intelligence algorithms for maximum power point tracking (MPPT)

This study examines the role of artificial intelligence in improving the efficiency of photovoltaic (PV) systems through maximum power point tracking (MPPT) under dynamic operating conditions. A simulation-based model was developed in MATLAB/Simulink to evaluate four AI-based MPPT methods, namely Artificial Neural Network (ANN), Fuzzy Logic Controller (FLC), Adaptive Neuro-Fuzzy Inference System (ANFIS), and Reinforcement Learning (RL), in comparison with conventional methods such as Perturb and Observe (P&O) and Incremental Conductance (INC). The results showed that AI-based techniques achieved better tracking efficiency, faster response time, lower oscillation, and reduced power loss than conventional controllers. Among the tested methods, Reinforcement Learning provided the best overall performance, while ANFIS showed highly competitive results with strong stability and fast convergence. These findings confirm that intelligent MPPT strategies can significantly enhance PV system efficiency and reliability.