Seamless Short‐ to Mid‐Term Probabilistic Wind Power Forecasting
Wind Energy · 2026-02 · 29 (2)
DOI: 10.1002/we.70079 ↗Kurz gefasst
Fachartikel in der Zeitschrift Wind Energy, online erschienen am 25.12.2025. Verfasst von Gabriel Dantas und 1 weiteren Autor:innen. Die Arbeit wurde bisher 6-mal zitiert (Crossref) und nennt 91 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
This paper brings a new understanding to the relative importance of different uncertainty sources across forecast horizons up to 7 days ahead. It presents a method for probabilistic wind power forecasting that quantifies uncertainty from weather forecasts and weather‐to‐power conversion separately. The study reveals that weather‐to‐power uncertainty is more significant for short‐term forecasts, while weather forecast uncertainty dominates mid‐term forecasts, with the transition point varying between wind farms. Offshore farms typically see this shift at shorter lead times than onshore. By addressing both uncertainty sources, the proposed forecast method achieves state‐of‐the‐art results for lead times of 6 to 162 h, eliminating the need for separate models for short‐ and mid‐term forecasting. Importantly, it also significantly improves short‐term forecasts during high weather uncertainty periods, where methods based on deterministic weather forecasts dramatically underestimate total uncertainty. The findings are supported by an extensive, reproducible case study comprising 73 wind farms in Great Britain over 5 years.
Zitieren
APA
Dantas, G., & Browell, J. (2026). Seamless Short‐ to Mid‐Term Probabilistic Wind Power Forecasting. Wind Energy, 29(2). https://doi.org/10.1002/we.70079
Vancouver
Dantas G, Browell J. Seamless Short‐ to Mid‐Term Probabilistic Wind Power Forecasting. Wind Energy. 2026;29(2). doi:10.1002/we.70079
BibTeX
@article{Dantas2026,
author = {Dantas, Gabriel and Browell, Jethro},
title = {Seamless Short‐ to Mid‐Term Probabilistic Wind Power Forecasting},
journal = {Wind Energy},
year = {2026},
volume = {29},
number = {2},
doi = {10.1002/we.70079}
}
EUVIMED