Machine learning-based wind speed time series analysis

Tahir Cetin Akinci, Oguzhan Topsakal, Andrew Wernerbach

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

3 Citations (Scopus)

Abstract

Machine Learning-based forecasting analysis provides high-accuracy results in estimating renewable energy sources. Having an accurate forecast of wind energy is essential to manage storage resources due to seasonal and geographical differences. In addition, the challenges posed by the discontinuity and uncertainty of wind power require accurate forecasts for energy economists and data scientists. In this study, hourly average wind speed data covering the years 2019, 2020, and 2021 in California were used to perform a time series analysis and forecasting utilizing one of the AutoML tools, Fedot. In addition, RMSE, MAE, and MAPE results were evaluated in the analyzes performed. Estimation results are consistent with these statistical evaluations.

Original languageEnglish
Title of host publicationIEEE Global Energy Conference, GEC 2022
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages391-394
Number of pages4
ISBN (Electronic)9781665497510
DOIs
Publication statusPublished - 2022
Externally publishedYes
Event2022 IEEE Global Energy Conference, GEC 2022 - Batman, Turkey
Duration: 26 Oct 202229 Oct 2022

Publication series

NameIEEE Global Energy Conference, GEC 2022

Conference

Conference2022 IEEE Global Energy Conference, GEC 2022
Country/TerritoryTurkey
CityBatman
Period26/10/2229/10/22

Bibliographical note

Publisher Copyright:
© 2022 IEEE.

Keywords

  • AutoML
  • deep learning
  • machine learning
  • time series analysis
  • wind prediction
  • wind speed

Fingerprint

Dive into the research topics of 'Machine learning-based wind speed time series analysis'. Together they form a unique fingerprint.

Cite this