Artificial neural network for maximum power point tracking used in solar photovoltaic system

Abstract

Nowadays, non-conventional energy sources like solar, wind, geothermal, and small hydro play a vital role in generating electricity. Among these, solar energy is utilized in urban and rural areas. When the sunlight falls on the solar plate, the PV cell produces charge carriers that produce an electric current. A photo voltaic cell is used when it works at the maximum power point. Traditional maximum power point tracking (MPPT) techniques are easier to structure and apply but perform worse than AI-based systems. The main objective of this paper is to develop an intelligent system to determine the maximum power point using artificial neural networks. This system uses the radial basis function network (RBFN) architecture to improve MPPT control for PV systems. The response characteristics of the photo-voltaic array are non-linear due to insolation, temperature variation, the incident light angle, and the solar cell's surface condition. Hence, this must be checked to develop the system's most significant amount of power. The MPPT controller's response can be recycled to monitor the DC-DC boost converters for maximum efficiency.