Advancing solar energy harvesting: Artificial intelligence approaches to maximum power point tracking

Abstract

This paper presents a comparative study of five maximum power point tracking (MPPT) control techniques in photovoltaic (PV) systems. The algorithms evaluated include classical methods, such as perturb and observe (P&O) and incremental conductance (IC), as well as intelligent approaches such as fuzzy logic (FL), artificial neural networks (ANNs), and adaptive neuro-fuzzy inference system (ANFIS). Intelligent methods provide faster response times and fewer oscillations around the maximum power point (MPP). The structure of the PV system includes a PV generator, load, and DC/DC boost converter driven by an MPPT controller. The performance of these techniques is analyzed under identical climatic conditions (same irradiation and temperature) in terms of efficiency, response time, response curve, accuracy in tracking the MPP, and others considered in this work. Simulations were performed using MATLAB-Simulink software, demonstrating that ANNs and ANFIS outperform traditional methods in dynamic environments, with FL being computationally intensive. P&O exhibited significant oscillations, while IC a showed slower tracking speed.