Exploring the Limits of Machine Learning in the Prediction of Solar Radiation

Giovanni Scabbia*, Antonio Sanfilippo, Daniel Perez-Astudillo, Dunia Bachour, Christos Fountoukis

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

1 Citation (Scopus)

Abstract

Predicting solar radiation at diverse time horizons is crucial for optimizing solar energy integration, ensuring grid stability, and regulating energy markets. Two main levels of time granularity are usually recognized as requiring different treatment: solar nowcasting for predictions up to 6 h, and solar forecasting for predictions beyond 6 h. Solar nowcasting typically relies on machine learning methods, while Numerical Weather Prediction (NWP) models are considered better suited for solar forecasting. The goal of this study was to explore the limits of machine learning in solar forecasting. Our results show that machine learning methods can be profitably used for predicting solar radiation beyond 6 h, with comparable performances to NWP models for day-ahead solar forecasting.

Original languageEnglish
Title of host publicationSustainable Energy-Water-Environment Nexus in Deserts - Proceeding of the 1st International Conference on Sustainable Energy-Water-Environment Nexus in Desert Climates
EditorsEssam Heggy, Veronica Bermudez, Marc Vermeersch
PublisherSpringer Nature
Pages381-384
Number of pages4
ISBN (Print)9783030760809
DOIs
Publication statusPublished - 2022
Event1st International Conference on Sustainable Energy-Water-Environment Nexus in Desert Climates, ICSEWEN 2019 - Ar-Rayyan, Qatar
Duration: 2 Dec 20195 Dec 2019

Publication series

NameAdvances in Science, Technology and Innovation
ISSN (Print)2522-8714
ISSN (Electronic)2522-8722

Conference

Conference1st International Conference on Sustainable Energy-Water-Environment Nexus in Desert Climates, ICSEWEN 2019
Country/TerritoryQatar
CityAr-Rayyan
Period2/12/195/12/19

Keywords

  • Autoregressive modeling
  • Differencing
  • Machine learning
  • Solar radiation forecasting

Fingerprint

Dive into the research topics of 'Exploring the Limits of Machine Learning in the Prediction of Solar Radiation'. Together they form a unique fingerprint.

Cite this