Neural Network based Robust Nonlinear GMPPT Control Approach for Partially Shadow Conditions of Solar Energy System

Abstract

Photovoltaic (PV) energy is making the hasty developments in the field of renewable energy systems. Solar energy is eco-friendly, easily accessible and everlasting. It is the utmost need of time to operate the PV system on maximum power point (MPP) just to extract the possible power from solar. Global maximum power point tracking (GMPPT) is the process of extracting maximum power from PV system under partially shaded conditions. This research article presents the nonlinear fractional integral terminal sliding mode (FITSMC) control paradigm for GMPPT of the PV system based DC-DC converter. Artificial Feedforward neural network (AFFNN) is utilized to generate the reference voltage for partial-shaded conditions. MATLAB/Simulink software is used for the entire simulations. Proposed controller technique performance is also tested under faulty conditions. Moreover, developed control scheme is compared with fundamental MPPT techniques i.e. proportional integral derivative (PID) controller and perturb and observe (P&O) technique with fault and without fault. The stability analysis is verified through Lyapunov criterion.