An ultra-short-term wind power robust prediction method considering the periodic impact of wind direction

Fuxiang Dong, Shiyu Ju, Jinfu Liu, Daren Yu and Hong Li

Renewable Energy, 2025, vol. 247, issue C

Abstract: The increasing magnitude of wind power integration into the grid amplifies its influence on grid stability. The optimal scheduling of the power grid needs precise power forecasting of wind farms. When employing wind power prediction results for scheduling, it is generally important to cautiously estimate the power output to prevent significant power deficits. This study introduces a novel wind power prediction approach incorporating adjustable robustness. The approach modifies the correlation between the predicted and the actual value using an asymmetric loss function. This adjustment enhances the ratio that the predicted value is lower than the actual value while minimizing the effect on the accuracy. Furthermore, given the periodic nature of the wind direction, a decoding method is used. This approach can enhance the understanding of the periodic features of wind direction. The results demonstrate that the proposed asymmetric loss function enhances the probability of the predicted wind power being lower than the actual value by 20.91 % when the asymmetric coefficient of the loss function is 0.3. Furthermore, the wind decoding method decreases the MAE (mean absolute error) by 3.82 %. In two additional datasets, the model exhibits the same effect, demonstrating the generalization capability of the developed approach.

Keywords: Wind power prediction; Wind energy; Robust prediction; Attention mechanism; Loss function (search for similar items in EconPapers)
Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
http://www.sciencedirect.com/science/article/pii/S0960148125006457
Full text for ScienceDirect subscribers only

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:eee:renene:v:247:y:2025:i:c:s0960148125006457

DOI: 10.1016/j.renene.2025.122983

Access Statistics for this article

Renewable Energy is currently edited by Soteris A. Kalogirou and Paul Christodoulides

More articles in Renewable Energy from Elsevier
Bibliographic data for series maintained by Catherine Liu ().