Estimation of maximum power generated from CIGS photovoltaic modules under non-uniform conditions

Author(s): Mabel U. Olanipekun*, Josiah L. Munda, Hens-Wien G. Chen, A. S Kumar
Tshwane University of Technology, Department of Electrical Engineering, Pretoria, 0001, South Africa
International Journal of Smart Grid and Clean Energy, vol. 3, no. 3, July 2014: pp. 318-324
ISSN: 2315-4462 (Print)
ISSN: 2373-3594 (Online)
Digital Object Identifier: 10.12720/sgce.3.3.318-324

Abstract: In this work, artificial neural network (ANN) is used to predict the output power generated from a single junction Cu(In,Ga)Se2 (CIGS) thin-film photovoltaic (PV) module by investigating the effect of the number of input variables on the estimated accuracy. The neural network structure used is based on using cell temperature and irradiation and two electrical parameters; the open circuit voltage and the short circuit current of the CIGS thin film PV module as its inputs with the predicted maximum power generation as its output. The proposed method uses the manufacturer’s data of the single junction CIGS thin film PV module NWCIGS-96. From the simulation results using ANN tools the average values for coefficient of determination (R2) = 0.8882, correlation coefficient (CC) = 0.9424, relative mean square error (RMSE) = 22.9034 and mean absolute error (MAE) = 19.0016.

Keywords: Artificial Neural Network, Estimated Power, PV module, Irradiation, Module Temperature, Open Circuit voltage, Short Circuit Current

Full Paper.pdf

Copyright © 2022 International Journal of Smart Grid and Clean Energy, All Rights Reserved