A robust deep learning framework for short-term wind power forecast of a full-scale wind farm using atmospheric variables

Short-term (less than 1 h) forecast of the power generated by wind turbines in a wind farm is extremely challenging due to the lack of reliable data from meteorological towers and numerical weather model outputs at these timescales. A robust deep learning model is developed for short-term forecasts...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	Energy (Oxford) Jg. 221; S. 119759
Hauptverfasser:	Meka, Rajitha, Alaeddini, Adel, Bhaganagar, Kiran
Format:	Journal Article
Sprache:	Englisch
Veröffentlicht:	Oxford Elsevier Ltd 15.04.2021 Elsevier BV
Schlagworte:	Deep learning Design of experiments Design optimization energy experimental design Mathematical models Neural networks Orthogonal array tuning method (OATM) Orthogonal arrays Robustness (mathematics) Short-term prediction Taguchi methods Temporal convolutional network (TCN) temporal variation Turbines Weather wind Wind farm power prediction Wind farms Wind power Wind speed Wind turbine Wind turbines Short-term prediction Neural networks Wind farm power prediction Wind turbine Temporal convolutional network (TCN) Orthogonal array tuning method (OATM)
ISSN:	0360-5442, 1873-6785
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Schreiben Sie den ersten Kommentar!