Data mining and statistical techniques for characterizing the performance of thin-film photovoltaic modules

作者：

Highlights：

• Data mining and statistical techniques are proposed for characterizing spectra.

• Using a statistical test we have proved the relationship among APE and spectra.

• Using k-means we have clustered all measured spectra in only five different types.

• We have explained photovoltaic modules performance using the proposed clusters.

摘要

•Data mining and statistical techniques are proposed for characterizing spectra.•Using a statistical test we have proved the relationship among APE and spectra.•Using k-means we have clustered all measured spectra in only five different types.•We have explained photovoltaic modules performance using the proposed clusters.

论文关键词：Solar spectral distribution,Photovoltaic modules,Performance ratio,Data mining,Statistical models

论文评审过程：Available online 5 July 2013.

论文官网地址：https://doi.org/10.1016/j.eswa.2013.06.059