Performance evaluation of the application of the genetic algorithm for tracking the maximum power point of a photovoltaic

Abstract

This diploma thesis focuses on evaluating the performance of the Genetic Algorithm (GA) for Maximum Power Point Tracking (MPPT) in a photovoltaic system. The aim is to optimize energy production by comparing this intelligent method with conventional approaches such as Perturb & Observe (P&O) and other intelligent techniques such as artificial neural networks (ANN), particularly in the presence of partial shading. Simulations were carried out in Matlab/Simulink to analyze the behavior of the three methods, followed by laboratory experimentation using the DSPACE 1104 card and the P&O method. The results showed that the genetic algorithm offers the best performance in terms of convergence speed and robustness, while highlighting the need to optimize its implementation for real-time applications