Performance Analysis of MPPT Tracking Algorithm Based on Artificial Neural Network for a PV Pumping System

The field of integrating renewable energies into elec-trical systems is increasingly vital, with photovoltaic technology playing a pivotal role, especially in irrigation research. This significance is attributed to the competitive cost of photovoltaic (PV) pumping systems in comparison to those reliant on fossil fuels. PV power generation systems frequently employ step-up converters to amplify the output voltage of solar panels, thereby achieving an optimal power operation point. The effective functioning of these converters hinges on a high-performance control algorithm. This study aims to conduct a comparative analysis of two maximum power point tracking (MPPT) controls: the Perturb and Observe (P and O) algorithm and the neural network (ANN) algorithm. The comparison seeks to ascertain which algorithm enhances control efficiency in PV systems, with particular emphasis on their application in irrigation. Simulation results prove that PV pumping system based on neural network MPPT control exhibits a quicker response time in reaching the maximum power compared to the P and O-controlled system. Furthermore, the P and O controlled system shows oscillations around Vmpp, which minimises system efficiency.