PV panel system modelling method based on neural network

In this paper, a nonlinear system of a photovoltaic (PV) module has been studied. Three types of Artificial Neural Network (ANN) time series are used for PV panel temperature prediction, these types are Nonlinear Autoregressive with External Input (NARX), Nonlinear Autoregressive (NAR) and Nonlinear...

Full description

Saved in:
Bibliographic Details
Main Authors: Khaleel, Fadi M., Hasan, Ibtisam A., Mohammed, Mohammed J.
Format: Conference Proceeding
Language:English
Subjects:
Ambient temperature
Artificial neural networks
Irradiance
Mathematical models
Modelling
Neural networks
Nonlinear systems
Parameters
Photovoltaic cells
Wind speed
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:In this paper, a nonlinear system of a photovoltaic (PV) module has been studied. Three types of Artificial Neural Network (ANN) time series are used for PV panel temperature prediction, these types are Nonlinear Autoregressive with External Input (NARX), Nonlinear Autoregressive (NAR) and Nonlinear Input-Output modelling methods. The input data parameters of the model were (ambient temperature, humidity, wind speed and irradiance), while the output data parameter was the PV panel temperature. All modelling techniques tested using Mean Square Error (MSE), and the results of them are compared with each other to conclude which method is the best. The results showed that NARX method documented the lowest MSE of 0.0557 while NAR and nonlinear input-output recorded 0.0560 and 1.5102 respectively.
ISSN:0094-243X
1551-7616
DOI:10.1063/5.0066820