A novel global MPP tracking scheme based on shading pattern identification using artificial neural networks for photovoltaic power generation during partial shaded condition

Efficiency of the photovoltaic (PV) power generating system is affected during partial shaded condition (PSC). The power-voltage characteristic of PV system exhibits multiple peaks during PSC. It is the task of maximum power point tracking (MPPT) controller to track global maximum power point (GMPP). Conventional MPPT schemes stop at first peak and fail to accomplish GMPP during PSC. Metaheuristic algorithms developed to track GMPP are complex, costly and require much time to track GMPP. Hence, this study put forwards a novel GMPPT scheme for effective tracking based on shading pattern identification using artificial neural network (ANN). In this scheme, ANN is used to estimate the shading pattern on PV panels and a two-dimensional lookup table supplies the MPP voltage corresponding to the shading pattern. By maintaining this voltage across PV panel, maximum power is extracted. The proposed scheme is compared with the existing artificial bee colony and particle swarm optimisation algorithms under different shading configurations to verify their performance under PSC. It is observed that the proposed scheme extracts maximum power effectively under various partial shading conditions. The proposed scheme is implemented in field-programmable gate array (FPGA) controller and the experimental results prove effectiveness of the proposed scheme.