A Novel Two Diode Model of Pv Module for MPPT with Neural Compensator

This paper deals with the improved model(Two Diode Model) of solar photovoltaic (SPV) module and back propagation neural network based maximum power point tracking (MPPT) for boost converter in a standalone photovoltaic system under variable temperature and insolation conditions. ie. The proposed model is robust to environment changes and load variations. Unlike Conventional solar-array mathematical model, Neural network modeling does not require any physical definitions for a photovoltaic array, hence they have a potential to provide a superior method of deriving non-linear models than the already established conventional techniques. In this paper back-propagation neural network trained model is employed to simulate and predict the maximum power point of a Photo Voltaic array using a random set of data collected from a real photovoltaic array. In order to validate the developed simulation model, simulated results from the proposed model under standard conditions are compared with specifications of commercially available USL Solar PV module (USP75) and BP-350U PV Modules. There is a very good agreement between the results. And the functioning of the proposed model and predicted maximum power point of the photo-voltaic array are evaluated by simulation using Matlab/simulink GUI environment.