An explainable multi-feature dimensionality reduction framework: Considering trend inconsistency in wind power sample

Offshore wind power prediction is significantly challenged by data quality issues arising from various factors such as environmental conditions and measurement errors, which severely compromise prediction accuracy and stability. This paper reveals a previously overlooked phenomenon in offshore wind...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	Energy (Oxford) Jg. 336; S. 138466
Hauptverfasser:	Meng, Anbo, Liu, Honghui, Xiao, Liexi, Tan, Zhenglin, Huang, Ziqian, Zhang, Qi, Yan, Baiping, Yin, Hao
Format:	Journal Article
Sprache:	Englisch
Veröffentlicht:	Elsevier Ltd 01.11.2025
Schlagworte:	Abnormal data Differential compensation dimensionality reduction Dimensionality reduction Offshore wind power prediction Sample trend inconsistency Dimensionality reduction Sample trend inconsistency Differential compensation dimensionality reduction Abnormal data Offshore wind power prediction
ISSN:	0360-5442
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Beschreibung
Zusammenfassung:	Offshore wind power prediction is significantly challenged by data quality issues arising from various factors such as environmental conditions and measurement errors, which severely compromise prediction accuracy and stability. This paper reveals a previously overlooked phenomenon in offshore wind power data, referred to as sample trend inconsistency, where dynamic offsets in meteorological features distort their expected physical relationship with power output. Such inconsistencies hinder the extraction of key features, disrupt feature–power coupling, and ultimately lead to degraded prediction performance. To address this issue, a Differential Compensation Dimensionality Reduction (DCDR) method is proposed to actively detect and mitigate trend inconsistencies during the dimensionality reduction process. Following normalized preprocessing of raw multi-feature meteorological data, the proposed DCDR method is employed to enhance sample trend consistency and perform dimensionality reduction by optimizing a selection coefficient to retain the most informative feature subset, which is then fed into deep learning models for training and accurate power forecasting. Experimental results demonstrate that DCDR achieves significant improvements over conventional dimensionality reduction methods, reducing RMSE and MAE by 21.1 % and 12.1 %, respectively. Furthermore, global feature importance analysis based on Shapley Additive Explanations (SHAP) confirms that the features retained by DCDR contribute more strongly to prediction accuracy and show improved consistency with the underlying physical relationships governing power output, thereby providing a more robust and interpretable framework that can enhance the operational reliability of offshore wind power forecasting models. •First identification of trend inconsistency in offshore wind power data (over 45 % occurrence) caused by dynamic offsets.•Proposed a novel dimensionality reduction strategy to reduce prediction errors by 21.1 % (RMSE) and 12.1 % (MAE).•Robust generalization to high-dimensional data and complex environments with optimal dimensionality selection.•Constructed an interpretability driven feature selection framework in offshore wind power prediction.
ISSN:	0360-5442
DOI:	10.1016/j.energy.2025.138466