Estimating the photovoltaic MPPT by artificial neural network

Abstract

The approach adopted in this study is to build a model of artificial neural network based on the architecture Multi-layer Perceptron (MLP) whose training is based on practical data. These are measured for a photovoltaic panel (PPV) around data acquisition chain composed of a certain number of sensors including temperature and global solar radiation. The objective is to track, in real time, the maximum power point (MPPT: Maximum Power Point Tracker) by using the model proposed MLP, directly from the Data irradiance namely G and the temperature T. This proposed modeling MLP is validated by using the statements measurements.