Performance of Artificial Neural Network and Particle Swarm Optimization Technique based Maximum Power Point Tracking for Photovoltaic System Under Different Environmental Conditions

Abstract

Photovoltaic (PV) array may receive different levels of solar irradiance and temperature under different environmental conditions, such as partially shaded by clouds or nearby building. However, all PV systems have two major drawbacks: the efficiency of PV power generation is very low and the output power of a PV system is nonlinear, which depends closely on weather conditions, such as ambient temperature and the solar irradiance. Hence, tracking the maximum power of the PV arrays at real time is very important to increase the whole system performance. Multiple peak power points occur when PV module is under partially shaded conditions, which would significantly reduce the energy produced by PV without proper control. Therefore, a Maximum Power Point Tracking (MPPT) algorithm is used to extract maximum available PV power from the PV array. However, most of the conventional MPPT algorithms are incapable to detect global peak (GP) power point with the presence of several local peaks (LP). A hybrid Artificial Neural Network and Particle Swarm Optimization (ANN-PSO) algorithm is proposed in this report to detect the global peak power. A PV system which consists of PV array, DC-DC boost converter, a hybrid ANN-PSO Algorithm, and a resistive load, is simulated using MATLAB/Simulink. The simulation results are carried out, compared and discussed. The proposed algorithm should perform well to detect the Global Peak of the PV array under different environmental conditions.