An Ultra‐Short‐Term Wind Power Forecasting Method Based on Adaptive Cleaning of Streaming Data and Differentiating of Input Feature Contributions

Yuhao Li; Chang Ge; Jie Yan

doi:10.1049/rpg2.70127

journal article Open Access Jan 01, 2025

An Ultra‐Short‐Term Wind Power Forecasting Method Based on Adaptive Cleaning of Streaming Data and Differentiating of Input Feature Contributions

Yuhao Li

Chang Ge

Jie Yan

IET Renewable Power Generation Vol. 19 No. 1 · Institution of Engineering and Technology (IET)

View at Publisher Save 10.1049/rpg2.70127

Abstract

ABSTRACT
Ultra‐short‐term wind power forecasting plays a crucial role in real‐time dispatching, frequency regulation, and intraday electricity market transactions. Forecasting accuracy heavily depends on data quality and feature informativeness. However, most existing studies conduct data cleaning offline, with limited attention to real‐time data quality during forecasting. Moreover, they often use historical power and NWP data uniformly, neglecting the time‐varying importance of input features. To address these issues, this paper proposes an ultra‐short‐term wind power forecasting method based on dynamic cleaning of streaming data anomalies and adaptive processing of input feature contributions. Firstly, similar samples of the current wind process are retrieved online via time series similarity matching, enabling real‐time anomaly detection in streaming data. Secondly, anomalous power sequences are reconstructed using a theoretical restoration model based on wind speed fluctuation identification. Finally, a forecasting architecture with personalised encoding and dynamically fused decoding is designed to enhance prediction accuracy. The proposed method has been successfully applied to a wind‐solar‐storage power station in Inner Mongolia, supporting both grid dispatching operations and daily maintenance. Compared to baseline methods, it achieves average reductions in forecasting errors of 0.59–9.99 percentage points for RMSE and 0.62–8.49 percentage points for MAE.

Topics

No keywords indexed for this article. Browse by subject →

References

32

[1]

(2024)

[2]

10.1016/j.rser.2022.112519

[3]

M.Leelavathi K. V.Suresh andB.Devi “Maximizing Solar Energy Output: A Comparative Analysis of MPPT Strategies for Partially Shaded PV Systems ” in2023 International Conference on Energy Materials and Communication Engineering (ICEMCE)(IEEE 2023) 1–7. 10.1109/icemce57940.2023.10434173

[4]

10.24425/bpasts.2024.150112

[5]

10.1016/j.apenergy.2019.01.193

[6]

10.1109/tpwrs.2023.3270662

[7]

10.1109/tpwrs.2023.3257368

[8]

10.1016/j.apenergy.2024.125212

[9]

10.1016/j.energy.2023.128947

[10]

10.1109/tste.2018.2822682

[11]

10.1063/5.0127640

[12]

10.1109/tste.2021.3138757

[13]

10.1109/tim.2020.3044719

[14]

10.1109/tste.2017.2717021

[15]

National Energy Administration (2022)

[16]

An adaptive identification method of abnormal data in wind and solar power stations

Haitao Wang, Ning Zhang, Ershun Du et al.

Renewable Energy 10.1016/j.renene.2023.03.081

[17]

10.1109/tste.2022.3198816

[18]

10.1016/j.energy.2023.127173

[19]

10.1016/j.energy.2022.124509

[20]

10.1109/tpwrs.2022.3224557

[21]

10.1109/access.2023.3332919

[22]

10.1109/tsg.2017.2763827

[23]

F.Ye J.Brodie T.Miles andA. A.Ezzat “Ultra‐Short‐Term Probabilistic Wind Forecasting: Can Numerical Weather Predictions Help? ” in2023 IEEE Power & Energy Society General Meeting (PESGM)(IEEE 2023) 1–5. 10.1109/pesgm52003.2023.10252311

[24]

10.1109/access.2020.3012306

[25]

10.1016/j.apenergy.2023.120815

[26]

10.1016/j.energy.2023.128986

[27]

A.Vaswani N.Shazeer N.Parmar et al. “Attention is All You Need ” preprint arXiv June 12 2017 https://doi.org/10.48550/arXiv.1706.03762.

[28]

Temporal Fusion Transformers for interpretable multi-horizon time series forecasting

Bryan Lim, Sercan Ö. Arık, Nicolas Loeff et al.

International Journal of Forecasting 10.1016/j.ijforecast.2021.03.012

[29]

D. A.Clevert T.Unterthiner andS.Hochreiter “Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUS) ” preprint arXiv November 23 2015 https://doi.org/10.48550/arXiv.1511.07289.

[30]

J. L.Ba J. R.Kiros andG. E.Hinton “Layer Normalization ” preprint arXiv July 16 2016 https://doi.org/10.48550/arXiv.1607.06450.

[31]

Y. N.Dauphin A.Fan M.Auli andD.Grangier “Language Modeling With Gated Convolutional Networks ” inInternational Conference on Machine Learning(PMLR 2017) 933–941.

[32]

Y.Bengio R.Ducharme andP.Vincent “A Neural Probabilistic Language Model ” inAdvances in Neural Information Processing Systems(NIPS 2000):932–938.

Metrics

0

Citations

32

References

Details

Published: Jan 01, 2025
Vol/Issue: 19(1)
License: View

Authors

Y

Yuhao Li

State Key Laboratory of Alternate Electrical Power System With Renewable Energy Sources (NCEPU) School of New Energy North China Electric Power University Beijing China

C

Chang Ge

State Key Laboratory of Alternate Electrical Power System With Renewable Energy Sources (NCEPU) School of New Energy North China Electric Power University Beijing China

J

Jie Yan

State Key Laboratory of Alternate Electrical Power System With Renewable Energy Sources (NCEPU) School of New Energy North China Electric Power University Beijing China

Funding

Beijing Nova Program Award: 20230484355

National Key Research and Development Program of China Award: 2022YFE0117600

Cite This Article

Yuhao Li, Chang Ge, Jie Yan (2025). An Ultra‐Short‐Term Wind Power Forecasting Method Based on Adaptive Cleaning of Streaming Data and Differentiating of Input Feature Contributions. IET Renewable Power Generation, 19(1). https://doi.org/10.1049/rpg2.70127

An Ultra‐Short‐Term Wind Power Forecasting Method Based on Adaptive Cleaning of Streaming Data and Differentiating of Input Feature Contributions

You May Also Like