Maximum Power Point Tracker for Photovoltaic Systems using On-line Learning Neural Networks

Abstract

this paper a new maximum-power-point-tracking (MPPT) controller for a photovoltaic (PV) energy conversion system is proposed. Nowadays, PV generation is more and more used as a renewable energy source. However, its main drawback is that PV generation is intermittent because it depends on shading conditions consequently irradiance value. Thus, the MPPT (Maximum Power Point Tracking Technique) together with the battery energy storage is necessary in order to obtain a stable and reliable maximum output power from a PV generation system. In our research work, the reference voltage for the MPPT is obtained by an artificial neural network (ANN) using the steepest negative gradient algorithm. The tracking algorithm adjusts the duty-cycle value of the dc/dc buck converter so that the PV-module voltage equals the voltage corresponding to the MPPT for any given realistic operation irradiance and temperature. The controller, which uses the classical perturb and observe (P&O) technique processes then the information gathered to a ANN controller bloc, which in turn generates the optimal value of the buck converter duty-cycle. The energy obtained from the converter is stored in a lithium-ion battery which feeds a useful load. The simulation results show the effectiveness of this method for the extraction of the maximum power available in the presence of different types of disturbances.