Artificial Neural Based Improved Maximum Power Point Tracking for PV Water Pumping System

Abstract

Maximum Power Point Tracking (MPPT) is used in Photovoltaic (PV) systems to ensuring operation at maximum power transfer from PV at different conditions of irradiation. In this study, Artificial Neural Network (ANN) is proposed to generate proper Pulse Width Modulation (PWM) signal to control the duty cycle of the DC-DC converter and hence to match both the load impedance and the PV impedance and hence ensure operation at maximum power. The input signals to ANN are the output power and the motor speed. To enhance the proposed method the weather is forecasted with ANN where the irradiation and the temperature data are generated using the Gaussian noise signal and this data is used to generate the output signal of ANN and this will increase the speed of controller response and the MPPT technique. The proposed system is consisting of PV source, DC-DC converter and DC motor which driving the centrifugal pump. MATLAB Simulink is used to demonstrate the feasibility of the ANN method under different operating conditions. The results show the effectiveness of the proposed technique to enhance ANN based MPPT for the PV pumping system.