Medium- and Long-term Forecast of Wind Farm Generation Power Based on Time Attention Transformer Approach

Wanze Ge

doi:10.54254/2755-2721/2026.TJ29826

Abstract

Accurate long-term wind power forecasting is crucial for ensuring stable power system operation and promoting renewable energy integration. However, existing forecasting models are often limited in their performance when processing wind power series due to inherent no stationarity and noise. They also face challenges such as inefficient modeling of long-sequence context and insufficient ability to capture long-term dependencies. To address these issues, this paper proposes a hybrid forecasting framework based on variational mode decomposition (VMD) and block-wise temporal attention (Time Attention). First, VMD is used to decompose the original highly volatile power series into a series of stationary and more regular intrinsic mode components (IMFs), effectively suppressing noise and reducing modeling complexity. Furthermore, a sequence-wise block-wise strategy is introduced to convert long series into local block token inputs, thus overcoming the context length limitations of traditional Transformers and enhancing the model's ability to capture long-term trends. Finally, a novel Time Attention mechanism is designed to explicitly model intra-module temporal dynamics and inter-modal correlations through hierarchical masks, enabling deeper feature extraction. To validate the effectiveness of the proposed framework, we conduct a comprehensive comparison with 12 mainstream baseline models on two public datasets. Experimental results show that in the task of predicting the next 96 time steps on Dataset 1, the mean squared error (MSE) of our model is reduced by 27.7% compared to the second-best Informer model, fully demonstrating the excellent capabilities and application potential of this framework in improving the accuracy and robustness of long-term wind power forecasting.

Keywords: wind power forecasting , long-term forecasting , hybrid model , data decomposition , deep learning

Article Information

Received: 17 November 2025

Published: 19 November 2025

DOI: https://doi.org/10.54254/2755-2721/2026.TJ29826

Article Type: Research Article

Cite this article

Ge,W. (2025). Medium- and Long-term Forecast of Wind Farm Generation Power Based on Time Attention Transformer Approach. Applied and Computational Engineering,207,36-54.

Data availability

The datasets used and/or analyzed during the current study will be available from the authors upon reasonable request.

Disclaimer/Publisher's Note

The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of EWA Publishing and/or the editor(s). EWA Publishing and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content.

About this Volume

Volume Title: ACE Vol.207

Part of Series: Applied and Computational Engineering

ISSN: 2755-2721 (Print) / 2755-273X (Online)

Copyright & License

[1]Hdidouan, D., & Staffell, I. (2017). The impact of climate change on the levelised cost of wind energy. Renewable Energy, 101, 575-592.

[2]Niu, S., Zhang, Z., Ke, X., Zhang, G., Huo, C., & Qin, B. (2022). Impact of renewable energy penetration rate on power system transient voltage stability. *Energy Reports, 8, 487-492.

[3]Burke, DJ, & O'Malley, MJ (2011). Factors influencing wind energy curtailment. IEEE Transactions on Sustainable Energy, 2(2), 185-193.

[4]Tawn, R., & Browell, J. (2022). A review of very short-term wind and solar power forecasting. Renewable and Sustainable Energy Reviews, 153, 111758.

[5]Monteiro, C., Bessa, R., Miranda, V., Botterud, A., Wang, J., & Conzelmann, G. (2009). Wind power forecasting: state-of-the-art 2009*. Argonne National Laboratory (ANL).

[6]Chen, Y., & Folly, KA (2018). Wind power forecasting. IFAC- PapersOnLine, 51(28), 414-419.

[7]Li L, Liu Yq, Yang Yp, Shuang H, Wang Ym. A physical approach of the shortterm wind power prediction based on CFD pre-calculated flow fields. J Hydrodyn Ser B 2013; 25(1): 56–61.

[8]Foley AM, Leahy PG, Marvuglia A, McKeogh EJ. Current methods and advances in forecasting of wind power generation. Renew Energy 2012; 37(1): 1–8.

[9]Eldali FA, Hansen TM, Suryanarayanan S, Chong EK. Employing ARIMA models to improve wind power forecasts: A case study in ERCOT. In: 2016 North American power symposium. NAPS, IEEE; 2016, p. 1–6.

[10]Kavasseri RG, Seetharaman K. Day-ahead wind speed forecasting using f-ARIMA models. Renew Energy 2009; 34(5): 1388–93.

[11]Hour-ahead wind power forecast based on random forests. Renew Energy 2017; 109: 529–41.

[12]Shi K, Qiao Y, Zhao W, Wang Q, Liu M, Lu Z. An improved random forest model of short-term wind-power forecasting to enhance accuracy, efficiency, and robustness. Wind Energy 2018; 21(12): 1383–94.

[13]Dowell J, Pinson P. Very-short-term probabilistic wind power forecasts by sparse vector autoregression. IEEE Trans Smart Grid 2015; 7(2): 763–70.

[14]Zhao Y, Ye L, Pinson P, Tang Y, Lu P. Correlation-constrained and sparsity-controlled vector autoregressive model for spatio -temporal wind power forecasting. IEEE Trans Power Syst 2018; 33(5): 5029–40.

[15]Application of support vector machine models for forecasting solar and wind energy resources: A review. J Clean Prod 2018; 199: 272–85.

[16]Jiang Y, Huang G. Short-term wind speed prediction: Hybrid of ensemble empirical mode decomposition, feature selection and error correction. Energy Convers Manage 2017; 144: 340–50.