Eintrag weiter verarbeiten

Short-term forecast of wind speed through mathematical models

Gespeichert in:

Veröffentlicht in: Energy reports 5(2019) vom: Nov., Seite 1172-1184
Personen und Körperschaften: Ferreira, Moniki (VerfasserIn), Cunha, Alexandre dos Santos (VerfasserIn), Lucio, Paulo (VerfasserIn)
Titel: Short-term forecast of wind speed through mathematical models/ Moniki Ferreira, Alexandre Santos, Paulo Lucio
Format: E-Book-Kapitel
Sprache: Englisch
veröffentlicht:
2019
Gesamtaufnahme: : Energy reports, 5(2019) vom: Nov., Seite 1172-1184
, volume:5
Schlagwörter:
Quelle: Verbunddaten SWB
Lizenzfreie Online-Ressourcen
Details
Zusammenfassung: The predictability of wind information in a given location is essential for the evaluation of a wind power project. Predicting wind speed accurately improves the planning of wind power generation, reducing costs and improving the use of resources. This paper seeks to predict the mean hourly wind speed in anemometric towers (at a height of 50 m) at two locations: a coastal region and one with complex terrain characteristics. To this end, the Holt-Winters (HW), Artificial Neural Networks (ANN) and Hybrid time-series models were used. Observational data evaluated by the Modern-Era Retrospective analysis for Research and Applications-Version 2 (MERRA-2) reanalysis at the same height of the towers. The results show that the hybrid model had a better performance in relation to the others, including when compared to the evaluation with MERRA-2. As such, the hybrid models are a good method to forecast wind speed data for wind generation.
ISSN: 2352-4847
DOI: 10.1016/j.egyr.2019.05.007