Artificial neural network based maximum power point tracking for solar photovoltaics

The nonlinear output of a photovoltaic (PV) panel under different irradiance and temperature values, poses a challenge for the design of Maximum power point trackers (MPPT). An MPPT optimizes the power being generated from a PV panel under varying environmental conditions by virtue of different algorithms which are controlling the duty cycle of the DC-DC converter. Conventionally hill climbing and open circuit voltage methods have been deployed for this purpose which provide a cheap and easy way of tracking, however their drawbacks are low accuracy, slow operation and periodic data logging. Artificial Neural Networks (ANN), however, can quickly and accurately estimate the output based on different data sets without falling trap to local maxima. This paper presents a comparative analysis between three MPPT techniques i.e. Perturb and Observe (P&O), Fractional open circuit voltage (FOCV) and the proposed ANN based technique. The model is trained using output data of maximum power point voltage (Vmpp) from a modelled PV array over different operating conditions of temperature and irradiance. An array of panels and MPPT models are simulated in MATLAB/Simulink at fixed resistive load, the results of which are compared with the effectiveness of the proposed method highlighted.