2024-03-28T10:25:51Zhttps://riubu.ubu.es/oai/requestoai:riubu.ubu.es:10259/57682022-11-21T11:57:53Zcom_10259_4393com_10259_5086com_10259_2604col_10259_4394
Granados López, Diego
Suárez García, Andrés
Diez Mediavilla, Montserrat
Alonso Tristán, Cristina
2021-05-17T11:58:37Z
2021-05-17T11:58:37Z
2021-04
0038-092X
http://hdl.handle.net/10259/5768
10.1016/j.solener.2021.02.039
There are several compilations of sky classifications that refer to Meteorological Indices (MIs) (variables usually recorded at meteorological ground stations), due to the scarcity of sky scanner devices that can supply the experimental data needed to apply the CIE standard sky classification. The use of one rather than another MI is never justified, because there is no standardized criterion for their selection. In this study, forty-three MIs, traditionally used to define different sky conditions, are reviewed. Feature Selection (FS) is a key step in the design of a sky-classification algorithm using MIs as an alternative to data from sky scanners. Four procedural methods for FS -Pearson, Permutation Importance, Recursive Feature Elimination, and Boruta- are applied to an extensive data set of MIs that includes CIE standard sky classification data, which was used as a reference. The use of FS procedures significatively reduced the original set of MIs, permitting the construction of different classification trees with high performance for the sky classification. In the case of the Pearson FS method, the classification tree only used two MIs. The advantage of the Pearson FS method is that it functions independently from the machine-learning algorithm used latter for the sky classification.
application/pdf
eng
Elsevier
Solar Energy. 2021, V. 218, p. 95-107
https://doi.org/10.1016/j.solener.2021.02.039
info:eu-repo/grantAgreement/JCyL/BU021G19
info:eu-repo/grantAgreement/MICINN/RTI2018-098900-B-I00
Attribution-NonCommercial-NoDerivatives 4.0 Internacional
http://creativecommons.org/licenses/by-nc-nd/4.0/
info:eu-repo/semantics/openAccess
CIE standard sky classification
Feature selection
Meteorological indices
Machine learning
Ingeniería eléctrica
Electric engineering
Feature selection for CIE standard sky classification
info:eu-repo/semantics/article
info:eu-repo/semantics/publishedVersion
Solar Energy
218
95
107