Machine learning techniques for daily solar energy prediction and interpolation using numerical weather models Articles uri icon

publication date

  • March 2016

start page

  • 1261

end page

  • 1274

issue

  • 4

volume

  • 28

international standard serial number (ISSN)

  • 1532-0626

electronic international standard serial number (EISSN)

  • 1532-0634

abstract

  • This article addresses two issues in solar energy forecasting from the numerical weather prediction (NWP) models using machine learning. First, we are interested in determining the relevant information for the forecasting task. With this purpose, a study has been carried out to evaluate the influence on accuracy of the number of NWP grid nodes used as input for the forecasting model, as well as their relative importance. Several machine learning (support vector machines and gradient boosting) and feature selection algorithms (linear, ReliefF, and local information analysis) have been used in this study. The second aim is to be able to predict solar energy for locations where no previous production data are available. To address this goal, an approach consisting on modeling regions in the grid is proposed. Models (aggregate models) use as input attributes the meteorological variables relevant for the region and two new inputs to identify the location of each station: the latitude and the longitude. Those models can be used to predict energy production for existing stations and for new locations, represented by latitude and longitude. Copyright (c) 2015 John Wiley & Sons, Ltd.

keywords

  • forecasting solar energy; solar energy interpolation; machine learning methods; support vector machines; feature selection