Neural Network Based Maximum Power Point Tracking Scheme for PV Systems Operating Under Partially Shaded Conditions

Photovoltaic (PV) Systems have gained significant attention due to its advantages like abundant availability, eco-friendly nature and low maintenance requirement. The P-V characteristic of the solar panel has a unique Maximum Power Point (MPP). To ensure that maximum power is extracted from the panels Maximum Power Point Tracking (MPPT) algorithm is utilized. In order to meet the voltage and current requirements large number of panels are connected in series-parallel combinations. The performance of such large arrays is adversely affected due to partial shading. This is due to the multiple peaks in the P-V Characteristics of the array under partial shading. Conventional MPPT algorithms have failed to detect the global peak under such conditions. Hence a Neural Network (NN) based MPPT algorithm has been proposed in this paper. The proposed algorithm has been verified by simulation for various partially shaded conditions and shown to perform well.