Photovoltaic module simulation by neural networks using solar spectral distribution
Article first published online: 15 MAY 2012
Copyright © 2012 John Wiley & Sons, Ltd.
Progress in Photovoltaics: Research and Applications
Volume 21, Issue 5, pages 1222–1235, August 2013
How to Cite
Piliougine, M., Elizondo, D., Mora-López, L. and de-Cardona, M. S.-. (2013), Photovoltaic module simulation by neural networks using solar spectral distribution. Prog. Photovolt: Res. Appl., 21: 1222–1235. doi: 10.1002/pip.2209
- Issue published online: 20 JUL 2013
- Article first published online: 15 MAY 2012
- neural network;
- multilayer perceptron;
- I-V curve;
- PV modeling;
- spectral distribution;
- average photon energy
A novel methodology based on artificial neural networks is proposed as an alternative to algebraic and numerical procedures to determine the I-V curve of a module under different conditions. Although there are methods that use neural networks for approximating the I-V curve, this is the first time that the measurement of the spectrum is incorporated as an input. In addition, a suitable selection of the training samples used to build the model is fundamental in order to get an accurate approximation. This is why a training sample selection based on a Kohonen self-organizing map is performed in this paper instead of a random selection. With the use of this preliminary step, the performance of the network trained with spectral information improves over the one without spectral information. Copyright © 2012 John Wiley & Sons, Ltd.