Gravitational Search Based Neural Network Tracking For Extraction Of Maximum Power Under Partial Shading Conditions In Pv System [articol]

Abstract

The output power produced by the solar cells shows a nonlinear current-voltage characteristic with respect to varying solar irradiance and ambient temperature. Maximum Power Point Tracking (MPPT) is utilized in Photovoltaic (PV) systems to maximize its output power. By monitoring the voltage and current of the PV system and controlling the duty cycle of the DC/ DC converter, a new MPPT controller is proposed in this paper. The design of MPPT is framed as an optimization problem whose solution is reached by using Gravitational search algorithm (GSA) to obtain the optimal parameters for the controller. Simulation results have shown that the proposed technique is delivering maximum power of photovoltaic system under different irradiance and ambient temperature. The performance of the developed GSA algorithm is comparable to Particle Swarm Optimization (PSO), Ant colony Optimization (ACO) for different conditions to validate its robustness.