Comparative Analysis of Intelligent MPPT Techniques Based on Fuzzy Logic and Neural Networks for Photovoltaic Systems
Photovoltaic systems, Fuzzy logic, MPPT, Artificial neural networks, Intelligent control.
The efficiency of photovoltaic systems is strongly influenced by variations in solar irradiance and temperature, making the use of Maximum Power Point Tracking (MPPT) algorithms essential. Different MPPT techniques exhibit distinct performances in terms of response speed, accuracy, and robustness under environmental changes, especially in dynamic operating conditions. This work aims to analyze and compare intelligent MPPT techniques applied to photovoltaic systems, with emphasis on methods based on fuzzy logic and artificial neural networks. The Perturb and Observe method is employed as a classical reference technique, enabling a comparative assessment of the performance of intelligent approaches relative to a widely adopted algorithm in the literature. The methodology is based on the modeling of a photovoltaic system in the MATLAB/Simulink environment, considering different operating conditions, including variations in irradiance and temperature, as well as partial shading scenarios. The performance of the algorithms is evaluated using criteria such as tracking efficiency, settling time, steady-state error, and dynamic behavior. The expected results aim to identify the advantages and limitations of intelligent techniques in comparison with the classical method, contributing to the selection of more efficient and robust MPPT strategies for photovoltaic applications.