Intelligent Nero modelling methods for PV panel system

Abstract

Nonlinear system identification modelling for the temperature of photovoltaic (PV) panel has been conducted in this work. In the beginning, an experimental work has been extracted from previous work in order to collect the input (ambient temperature, humidity, irradiance and wind speed) and output (PV module temperature) parameters. Then, Neural Network time series and Adaptive Neuro-Fuzzy Inference System (ANFIS) models represented as system identification method to predict the temperature of PV panel as an output for the system. Both of modelling methods verified using mean square error (MSE). The effectiveness of all methods has been compared to know which method is the batter. Finally, the achieved results stated that the ANFIS method recorded the lowest MSE of 2.2627*10−7 compared with NARX method which recorded of 5.078. ANFIS technique proved that will be able to use it in the control process in future.