A MAXIMUM POWER POINT TRACKING METHOD BASED ON ARTIFICIAL NEURAL NETWORK FOR A PV SYSTEM

Solar photovoltaic system characteristics depends on environmental factors, therefore a maximum power point tracking MPPT technique is needed to keep the working point of the system as close as possible to the MPP. In this paper we present a PV generator composed by four PV panel Kaneka GSA211 (60Watt) placed in series, and a neural network model developed by the authors. The aim of this study focuses on the application of the artificial neural networks to extract the maximum power point of a photovoltaic generator that feeds a motorpump group unit through a PWM inverter installed in the laboratory. The output of the ANN is the optimal voltage Vopt which is compared to the PV generator voltage Vpv, then passed through an integrator to extract the stator frequency fs that are given to the PWM control of the DC-AC inverter to find out the sinusoidal reference voltage and the sampled wave. The training of the ANN is done with Levenberg Marquardt algorithm and the whole technique is being simulated and studied using MATLAB software [24].