KIT | KIT-Bibliothek | Impressum | Datenschutz

Potential of Ensemble Copula Coupling for Wind Power Forecasting

Phipps, Kaleb; Ludwig, Nicole; Hagenmeyer, Veit; Mikut, Ralf

Abstract (englisch):
With the share of renewable energy sources in the energy system increasing,accurate wind power forecasts are required to ensure a balanced supply anddemand. Wind power is, however, highly dependent on the chaotic weathersystem and other stochastic features. Therefore, probabilistic wind powerforecasts are essential to capture uncertainty in the model parameters and inputfeatures. The weather and wind power forecasts are generally post-processedto eliminate some of the systematic biases in the model and calibrate it topast observations. While this is successfully done for wind power forecasts,the approaches used often ignore the inherent correlations among the weathervariables. The present paper, therefore, extends the previous post-processingstrategies by including Ensemble Copula Coupling (ECC) to restore the de-pendency structures between variables and investigates, whether including thedependency structures changes the optimal post-processing strategy. We findthat the optimal post-processing strategy does not change when including ECCand ECC does not improve the forecast accuracy when the dependency struc-tures are weak. ... mehr

Open Access Logo


Verlagsausgabe §
DOI: 10.5445/IR/1000127955
Veröffentlicht am 22.12.2020
Cover der Publikation
Zugehörige Institution(en) am KIT Institut für Automation und angewandte Informatik (IAI)
Publikationstyp Proceedingsbeitrag
Publikationsjahr 2020
Sprache Englisch
Identifikator ISBN: 978-3-7315-1051-2
KITopen-ID: 1000127955
Erschienen in Proceedings - 30. Workshop Computational Intelligence : Berlin, 26. - 27. November 2020
Veranstaltung 30. Workshop Computational Intelligence (2020), Berlin, 26.11.2020 – 27.11.2020
Verlag KIT Scientific Publishing
Seiten 87-109
Relationen in KITopen
KIT – Die Forschungsuniversität in der Helmholtz-Gemeinschaft
KITopen Landing Page