A Hybrid Maximum Power Point Tracking Technique for Partially Shaded Photovoltaic Arrays

Abstract

This paper introduces a hybrid maximum power point tracking (MPPT) technique for photovoltaic (PV) arrays working under partial shading conditions. This new algorithm can combine a traditional MPPT algorithm, such as perturb and observe, or incremental conductance, with the artificial neural network (ANN) technique. The proposed hybrid MPPT algorithm is based on the ANN and used to predict the global MPP region by estimating its voltage boundaries. Consequently, the conventional MPPT algorithm searches for the MPP in the predicted region. The proposed technique is modeled and simulated using MATLAB/Simulink. The results show the effectiveness of the proposed hybrid MPPT technique to track the global MPP accurately with a rapid response comparing to the ANN; this increases the output power level of the PV array under various shading patterns.