Artificial neural network (ANN) and adaptive neuro-fuzzy inference system (ANFIS): application for a photovoltaic system under unstable environmental conditions

In this paper, artificial neural network (ANN) and adaptive neuro-fuzzy inference system (ANFIS) are used as maximum power point tracking controllers to improve the performance of a stand-alone photovoltaic system. Based on the FL-M-160W PV module specifications, the PV panel and the boost converter were modeled in MATLAB/Simulink environment. Using a set of data collected during the experimental phase, the developed ANN and ANFIS-MPPT controllers have being learn, test and validate offline then inserted into the PV system. These controllers deliver at output an optimal voltage which will be compared to the reference voltage supplied by the photovoltaic generator and the error obtained will be used to adjust the duty cycle of the converter boost located between the PV panel and the load. It is shown after simulations that ANN and ANFIS-MPPT controllers are more robust and can follow the maximum power point with very low recovery time and low oscillations around the operating point in both in stable and changing atmospheric conditions.