Volume 9, Issue 4, December 2014, Pages 1869–1877
Fayrouz DKHICHI1 and Benyounes OUKARFI2
1 Department of Electrical Engineering, EEA&TI laboratory, Faculty of Sciences and Techniques, Hassan II University, Mohammedia, Morocco
2 Department of Electrical Engineering, EEA&TI laboratory, Faculty of Sciences and Techniques, Hassan II University, Mohammedia, Morocco
Original language: English
Copyright © 2014 ISSR Journals. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
This present paper deals with the parameter determination of solar cell under different values of irradiance and temperature by using an artificial neural network. This latter is trained by an optimization algorithm based on gradient descent. In this work we used two distinguished algorithms from different order of gradient descent: Levenberg-Marquardt and conjugate gradient. The use of these two algorithms is to conduct a comparative study on their performances. The results revealed that the Levenberg-Marquardt algorithm presents the best potential in providing accurate electrical parameters values compared to conjugate gradient algorithm. Moreover, the trends of electrical parameters according to irradiance and temperature show the effect of each of these two meteorological factors on the values of the intrinsic parameters of solar cell.
Author Keywords: Artificial neural network, Conjugate gradient, Electrical parameters, Levenberg-Marquardt, Solar cell.
Fayrouz DKHICHI1 and Benyounes OUKARFI2
1 Department of Electrical Engineering, EEA&TI laboratory, Faculty of Sciences and Techniques, Hassan II University, Mohammedia, Morocco
2 Department of Electrical Engineering, EEA&TI laboratory, Faculty of Sciences and Techniques, Hassan II University, Mohammedia, Morocco
Original language: English
Copyright © 2014 ISSR Journals. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Abstract
This present paper deals with the parameter determination of solar cell under different values of irradiance and temperature by using an artificial neural network. This latter is trained by an optimization algorithm based on gradient descent. In this work we used two distinguished algorithms from different order of gradient descent: Levenberg-Marquardt and conjugate gradient. The use of these two algorithms is to conduct a comparative study on their performances. The results revealed that the Levenberg-Marquardt algorithm presents the best potential in providing accurate electrical parameters values compared to conjugate gradient algorithm. Moreover, the trends of electrical parameters according to irradiance and temperature show the effect of each of these two meteorological factors on the values of the intrinsic parameters of solar cell.
Author Keywords: Artificial neural network, Conjugate gradient, Electrical parameters, Levenberg-Marquardt, Solar cell.
How to Cite this Article
Fayrouz DKHICHI and Benyounes OUKARFI, “Levenberg-Marquardt and Conjugate Gradient Training Algorithms of Neural Network for Parameter Determination of Solar Cell,” International Journal of Innovation and Applied Studies, vol. 9, no. 4, pp. 1869–1877, December 2014.
