Radial Basis Function Neural Network Technique for Efficient Maximum Power Point Tracking in Solar Photo-Voltaic System

摘要

To harness electricity from solar photo-voltaic (SPV) cell at maximum power point is the challenge for researcher. Artificial Intelligence (AI) plays a major role in control and estimation, hence, if trained properly the AI system can provide accurate solutions. Since the fast maximum power point tracking (MPPT) of SPV system is desirable, the RBFNN MPPT algorithm that has the advantage of universal approximation and fast learning is designed using Gaussian activation function and compared with conventional perturb and observe (P&O), back propagation neural network (BPNN) in this paper. The system is tested for MPPT operation on different values of irradiances and a comparative evaluation of power tracking efficiency, settling time, ripple content, average power loss is presented for the SPV system to validate the proposed algorithm.