IDEAS home Printed from https://ideas.repec.org/a/eee/energy/v339y2025ics0360544225047206.html

Hybrid ultra-short-term wind speed forecasting model based on improved BO-HMA-BiGRU and GMBInformer: Integrating SVMD-SWT dual decomposition and MPE-driven modeling mechanism

Author

Listed:
  • Fu, Zhengze
  • Qian, Hongliang
  • Chu, Xuanxuan
  • Yang, Fan
  • Guo, Chengchao
  • Wang, Fuming

Abstract

Accurate ultra-short-term wind speed forecasting is essential for ensuring the stable and efficient integration of wind energy into power systems. This paper proposes a novel hybrid framework, termed STBHBI (Spectral-validated Two-stage decomposition with MPE-based complexity-driven assignment and a Bayesian-optimized Hierarchical Multi-attention BiGRU – GMBInformer hybrid), which integrates spectral-validated variational mode decomposition (SVMD), stationary wavelet transform (SWT), multi-scale permutation entropy (MPE), and two newly designed deep learning models: the Bayesian-optimized hierarchical multi-attention BiGRU (BO-HMA-BiGRU) and the gated multi-scale Informer with relative position bias (GMBInformer). The forecasting process begins with SVMD to decompose wind speed sequences into intrinsic mode functions (IMFs), while spectral error analysis captures high-frequency residual information. The residuals are further decomposed using SWT to recover signal components lost in the high-frequency band. MPE is then employed to assess the complexity of each IMF, guiding the adaptive allocation of forecasting models: low-complexity components are fed into BO-HMA-BiGRU, while high-complexity and high-frequency components are predicted by GMBInformer. Extensive experiments conducted on four seasonal datasets from a wind plant in Guangdong Province and an dataset from a wind plant in Gansu Province, China demonstrate that the STBHBI model significantly outperforms baseline models across key metrics including R2, MSE, RMSE, MAE, and MAPE, consistently achieving R2 scores above 0.99. Ablation studies further validate the contributions of the hierarchical attention mechanism, multi-scale convolutional structures, and gated fusion strategy, revealing that these modules work synergistically to enhance multi-frequency feature extraction and model robustness. This study highlights the critical role of multi-stage signal decomposition and hybrid deep learning in improving ultra-short-term wind speed forecasting under complex seasonal and regional environmental conditions, offering an effective and robust tool for wind energy scheduling and grid operation.

Suggested Citation

  • Fu, Zhengze & Qian, Hongliang & Chu, Xuanxuan & Yang, Fan & Guo, Chengchao & Wang, Fuming, 2025. "Hybrid ultra-short-term wind speed forecasting model based on improved BO-HMA-BiGRU and GMBInformer: Integrating SVMD-SWT dual decomposition and MPE-driven modeling mechanism," Energy, Elsevier, vol. 339(C).
    • Handle: RePEc:eee:energy:v:339:y:2025:i:c:s0360544225047206
    DOI: 10.1016/j.energy.2025.139078
    as

    Download full text from publisher

    File URL: http://www.sciencedirect.com/science/article/pii/S0360544225047206
    Download Restriction: Full text for ScienceDirect subscribers only
    File URL: https://libkey.io/10.1016/j.energy.2025.139078?utm_source=ideas
    LibKey link: if access is restricted and if your library uses this service, LibKey will redirect you to where you can use your library subscription to access this item
    ---><---

    As the access to this document is restricted, you may want to

    for a different version of it.

    References listed on IDEAS

    as
    1. Xu, Xuefang & Hu, Shiting & Shao, Huaishuang & Shi, Peiming & Li, Ruixiong & Li, Deguang, 2023. "A spatio-temporal forecasting model using optimally weighted graph convolutional network and gated recurrent unit for wind speed of different sites distributed in an offshore wind farm," Energy, Elsevier, vol. 284(C).
    2. Mengran Zhou & Tianyu Hu & Kai Bian & Wenhao Lai & Feng Hu & Oumaima Hamrani & Ziwei Zhu, 2021. "Short-Term Electric Load Forecasting Based on Variational Mode Decomposition and Grey Wolf Optimization," Energies, MDPI, vol. 14(16), pages 1-17, August.
    3. Leng, Zhiyuan & Chen, Lu & Yi, Bin & Liu, Fanqian & Xie, Tao & Mei, Ziyi, 2025. "Short-term wind speed forecasting based on a novel KANInformer model and improved dual decomposition," Energy, Elsevier, vol. 322(C).
    4. Xu, Xuefang & Hu, Shiting & Shi, Peiming & Shao, Huaishuang & Li, Ruixiong & Li, Zhi, 2023. "Natural phase space reconstruction-based broad learning system for short-term wind speed prediction: Case studies of an offshore wind farm," Energy, Elsevier, vol. 262(PA).
    5. Chia-Hung Wang & Qigen Zhao & Rong Tian, 2023. "Short-Term Wind Power Prediction Based on a Hybrid Markov-Based PSO-BP Neural Network," Energies, MDPI, vol. 16(11), pages 1-24, May.
    6. Liu, Xiaolei & Lin, Zi & Feng, Ziming, 2021. "Short-term offshore wind speed forecast by seasonal ARIMA - A comparison against GRU and LSTM," Energy, Elsevier, vol. 227(C).
    7. Meftah Elsaraiti & Adel Merabet, 2021. "A Comparative Analysis of the ARIMA and LSTM Predictive Models and Their Effectiveness for Predicting Wind Speed," Energies, MDPI, vol. 14(20), pages 1-16, October.
    8. Xu, Li & Ou, Yanxia & Cai, Jingjing & Wang, Jin & Fu, Yang & Bian, Xiaoyan, 2023. "Offshore wind speed assessment with statistical and attention-based neural network methods based on STL decomposition," Renewable Energy, Elsevier, vol. 216(C).
    9. Wang, Han & Han, Shuang & Liu, Yongqian & Yan, Jie & Li, Li, 2019. "Sequence transfer correction algorithm for numerical weather prediction wind speed and its application in a wind power forecasting system," Applied Energy, Elsevier, vol. 237(C), pages 1-10.
    10. Liu, Tianhao & Lv, Kunye & Chen, Fengjie & Goh, Hui Hwang & Kurniawan, Tonni Agustiono & Hu, Ruifeng & Jiang, Meihui & Zhang, Dongdong, 2024. "Wind power curve model combining smoothed spline with first-order moments and density-adjusted wind speed strategy," Energy, Elsevier, vol. 313(C).
    11. Duan, Jiandong & Wang, Peng & Ma, Wentao & Tian, Xuan & Fang, Shuai & Cheng, Yulin & Chang, Ying & Liu, Haofan, 2021. "Short-term wind power forecasting using the hybrid model of improved variational mode decomposition and Correntropy Long Short -term memory neural network," Energy, Elsevier, vol. 214(C).
    12. Zhang, Guowei & Zhang, Yi & Wang, Hui & Liu, Da & Cheng, Runkun & Yang, Di, 2024. "Short-term wind speed forecasting based on adaptive secondary decomposition and robust temporal convolutional network," Energy, Elsevier, vol. 288(C).
    13. Zhang, Haipeng & Wang, Jianzhou & Qian, Yuansheng & Li, Qiwei, 2024. "Point and interval wind speed forecasting of multivariate time series based on dual-layer LSTM," Energy, Elsevier, vol. 294(C).
    14. Zhao, Jing & Guo, Yiyi & Lin, Yihua & Zhao, Zhiyuan & Guo, Zhenhai, 2024. "A novel dynamic ensemble of numerical weather prediction for multi-step wind speed forecasting with deep reinforcement learning and error sequence modeling," Energy, Elsevier, vol. 302(C).
    15. Wang, Yaqi & Zhao, Xiaomeng & Li, Zheng & Zhu, Wenbo & Gui, Renzhou, 2024. "A novel hybrid model for multi-step-ahead forecasting of wind speed based on univariate data feature enhancement," Energy, Elsevier, vol. 312(C).
    16. Fu, Zhengze & Qian, Hongliang & Wei, Wei & Chu, Xuanxuan & Yang, Fan & Guo, Chengchao & Wang, Fuming, 2025. "An Informer-BiGRU-temporal attention multi-step wind speed prediction model based on spatial-temporal dimension denoising and combined VMD decomposition," Energy, Elsevier, vol. 326(C).
    17. Ullah, Sajid & Chen, Xi & Han, Han & Wu, Junhao & Dong, Jinghan & Liu, Ruiqing & Ding, Weijie & Liu, Min & Li, Qingli & Qi, Honggang & Huang, Yonggui & Yu, Philip Lh, 2025. "A novel hybrid ensemble approach for wind speed forecasting with dual-stage decomposition strategy using optimized GRU and transformer models," Energy, Elsevier, vol. 329(C).
    18. Qian, Zheng & Pei, Yan & Zareipour, Hamidreza & Chen, Niya, 2019. "A review and discussion of decomposition-based hybrid models for wind energy forecasting applications," Applied Energy, Elsevier, vol. 235(C), pages 939-953.
    19. Cassola, Federico & Burlando, Massimiliano, 2012. "Wind speed and wind energy forecast through Kalman filtering of Numerical Weather Prediction model output," Applied Energy, Elsevier, vol. 99(C), pages 154-166.
    20. Shu, Zhiyong & Lei, Gang & Liang, Wenqing & Huang, Lei & Che, Bangxiang & Zheng, Xiaohong & Qian, Hua, 2024. "Rapid prediction of water hammer characteristics in liquid hydrogen storage and transportation systems: A theoretical model," Renewable Energy, Elsevier, vol. 230(C).
    21. Sun, Xiaoying & Liu, Haizhong, 2024. "Multivariate short-term wind speed prediction based on PSO-VMD-SE-ICEEMDAN two-stage decomposition and Att-S2S," Energy, Elsevier, vol. 305(C).
    22. Nantian Huang & Chong Yuan & Guowei Cai & Enkai Xing, 2016. "Hybrid Short Term Wind Speed Forecasting Using Variational Mode Decomposition and a Weighted Regularized Extreme Learning Machine," Energies, MDPI, vol. 9(12), pages 1-19, November.
    23. Hu, Huanling & Wang, Lin & Tao, Rui, 2021. "Wind speed forecasting based on variational mode decomposition and improved echo state network," Renewable Energy, Elsevier, vol. 164(C), pages 729-751.
    24. Boutoubat, M. & Mokrani, L. & Machmoum, M., 2013. "Control of a wind energy conversion system equipped by a DFIG for active power generation and power quality improvement," Renewable Energy, Elsevier, vol. 50(C), pages 378-386.
    25. Shi, Peiming & Lin, Shengmao & Song, Dongran & Xu, Xuefang & Wu, Jie, 2024. "TRNet: A trend and residual network utilizing novel hilly attention mechanism for wind speed prediction in complex scenario," Energy, Elsevier, vol. 309(C).
    26. Zachary M. Smith & Bertrand Delgutte & Andrew J. Oxenham, 2002. "Chimaeric sounds reveal dichotomies in auditory perception," Nature, Nature, vol. 416(6876), pages 87-90, March.
    27. Liang, Yang & Zhang, Dongqin & Zhang, Jize & Hu, Gang, 2024. "A state-of-the-art analysis on decomposition method for short-term wind speed forecasting using LSTM and a novel hybrid deep learning model," Energy, Elsevier, vol. 313(C).
    28. Shahid, Farah & Zameer, Aneela & Muneeb, Muhammad, 2021. "A novel genetic LSTM model for wind power forecast," Energy, Elsevier, vol. 223(C).
    29. Zhang, Yagang & Pan, Guifang & Chen, Bing & Han, Jingyi & Zhao, Yuan & Zhang, Chenhong, 2020. "Short-term wind speed prediction model based on GA-ANN improved by VMD," Renewable Energy, Elsevier, vol. 156(C), pages 1373-1388.
    30. Yang, Wendong & Zang, Xinyi & Wu, Chunying & Hao, Yan, 2024. "A new multi-objective ensemble wind speed forecasting system: Mixed-frequency interval-valued modeling paradigm," Energy, Elsevier, vol. 304(C).
    31. Li, Jingrui & Wang, Jianzhou & Zhang, Haipeng & Li, Zhiwu, 2022. "An innovative combined model based on multi-objective optimization approach for forecasting short-term wind speed: A case study in China," Renewable Energy, Elsevier, vol. 201(P1), pages 766-779.
    32. Che, Jinxing & Yuan, Fang & Deng, Dewen & Jiang, Zheyong, 2023. "Ultra-short-term probabilistic wind power forecasting with spatial-temporal multi-scale features and K-FSDW based weight," Applied Energy, Elsevier, vol. 331(C).
    33. Zhang, Shuai & Chen, Yong & Xiao, Jiuhong & Zhang, Wenyu & Feng, Ruijun, 2021. "Hybrid wind speed forecasting model based on multivariate data secondary decomposition approach and deep learning algorithm with attention mechanism," Renewable Energy, Elsevier, vol. 174(C), pages 688-704.
    Full references (including those not matched with items on IDEAS)

    Most related items

    These are the items that most often cite the same works as this one and are cited by the same works as this one.
    1. Jiang, Wei & Lu, Qi & Xu, Yanhe & Chen, Zhong & Gong, Ting, 2025. "Short-term wind speed prediction based on denoising algorithm of enhanced successive variational mode decomposition and integrated parallel prediction model," Energy, Elsevier, vol. 338(C).
    2. Zeng, Huanze & Wu, Binrong & Fang, Haoyu & Lin, Jiacheng, 2025. "Interpretable wind speed forecasting through two-stage decomposition with comprehensive relative importance analysis," Applied Energy, Elsevier, vol. 392(C).
    3. Liu, Zhi-Feng & Liu, You-Yuan & Chen, Xiao-Rui & Zhang, Shu-Rui & Luo, Xing-Fu & Li, Ling-Ling & Yang, Yi-Zhou & You, Guo-Dong, 2024. "A novel deep learning-based evolutionary model with potential attention and memory decay-enhancement strategy for short-term wind power point-interval forecasting," Applied Energy, Elsevier, vol. 360(C).
    4. Yang, Dongchuan & Li, Mingzhu & Guo, Ju-e & Du, Pei, 2024. "An attention-based multi-input LSTM with sliding window-based two-stage decomposition for wind speed forecasting," Applied Energy, Elsevier, vol. 375(C).
    5. Wu, Xiaobang & Wang, Deguang & Yang, Ming & Liang, Chengbin, 2025. "CEEMDAN-SE-HDBSCAN-VMD-TCN-BiGRU: A two-stage decomposition-based parallel model for multi-altitude ultra-short-term wind speed forecasting," Energy, Elsevier, vol. 330(C).
    6. Wu, Jie & Jin, Yuhao & Luo, Wenjun, 2025. "Prior and synergistic effects in multi-source information fusion for optimal wind speed forecasting model selection," Energy, Elsevier, vol. 337(C).
    7. Li, Yanhui & Sun, Kaixuan & Yao, Qi & Wang, Lin, 2024. "A dual-optimization wind speed forecasting model based on deep learning and improved dung beetle optimization algorithm," Energy, Elsevier, vol. 286(C).
    8. Xu, Rui & Fang, Haoyu & Zeng, Huanze & Wu, Binrong, 2025. "A novel interpretable wind speed forecasting based on the multivariate variational mode decomposition and temporal fusion transformer," Energy, Elsevier, vol. 331(C).
    9. Wang, Yun & Zou, Runmin & Liu, Fang & Zhang, Lingjun & Liu, Qianyi, 2021. "A review of wind speed and wind power forecasting with deep neural networks," Applied Energy, Elsevier, vol. 304(C).
    10. Li, Dan & Jiang, Fuxin & Chen, Min & Qian, Tao, 2022. "Multi-step-ahead wind speed forecasting based on a hybrid decomposition method and temporal convolutional networks," Energy, Elsevier, vol. 238(PC).
    11. Tan, Jiawei & Zhu, Hong & Zhang, Jingrui & Liu, Houde, 2025. "Multi-stage wind speed prediction with CEEMDAN-SE-IDBO-LSTM based on rolling decomposition," Energy, Elsevier, vol. 338(C).
    12. Verdone, Alessio & Panella, Massimo & De Santis, Enrico & Rizzi, Antonello, 2025. "A review of solar and wind energy forecasting: From single-site to multi-site paradigm," Applied Energy, Elsevier, vol. 392(C).
    13. Wu, Binrong & Wang, Lin & Zeng, Yu-Rong, 2022. "Interpretable wind speed prediction with multivariate time series and temporal fusion transformers," Energy, Elsevier, vol. 252(C).
    14. Zhang, Chu & Ji, Chunlei & Hua, Lei & Ma, Huixin & Nazir, Muhammad Shahzad & Peng, Tian, 2022. "Evolutionary quantile regression gated recurrent unit network based on variational mode decomposition, improved whale optimization algorithm for probabilistic short-term wind speed prediction," Renewable Energy, Elsevier, vol. 197(C), pages 668-682.
    15. Li, Mingjun & Zhang, Kequan & Kou, Menggang & Ma, Yining, 2025. "An offshore wind speed forecasting system based on feature enhancement, deep time series clustering, and extended LSTM," Energy, Elsevier, vol. 333(C).
    16. Xu, Hao & Zhu, Zhenhao & Liu, Hongbing & Zio, Enrico & Qiu, Xiaolong & Lu, Yuchen & Qu, Xianqiang, 2025. "Spectral dynamic aggregation transformer and fitted swing-door algorithm for wind power monitoring," Energy, Elsevier, vol. 341(C).
    17. Zhang, Yagang & Wang, Hui & Wang, Jingchao & Cheng, Xiaodan & Wang, Tong & Zhao, Zheng, 2024. "Ensemble optimization approach based on hybrid mode decomposition and intelligent technology for wind power prediction system," Energy, Elsevier, vol. 292(C).
    18. Cheng, Runkun & Yang, Di & Liu, Da & Zhang, Guowei, 2024. "A reconstruction-based secondary decomposition-ensemble framework for wind power forecasting," Energy, Elsevier, vol. 308(C).
    19. Zhang, Yagang & Zhang, Jinghui & Yu, Leyi & Pan, Zhiya & Feng, Changyou & Sun, Yiqian & Wang, Fei, 2022. "A short-term wind energy hybrid optimal prediction system with denoising and novel error correction technique," Energy, Elsevier, vol. 254(PC).
    20. Shi, Zhihan & Zhang, Guangming & Lu, Chao & Zhou, Xiaoxiong & Lv, Xiaodong, 2025. "Dynamic Spatio-Temporal Graph-Enhanced KANformer for high-fidelity ultra-short-term wind power forecasting," Energy, Elsevier, vol. 337(C).

    More about this item

    Keywords

    ;
    ;
    ;
    ;
    ;

    Statistics

    Access and download statistics

    Corrections

    All material on this site has been provided by the respective publishers and authors. You can help correct errors and omissions. When requesting a correction, please mention this item's handle: RePEc:eee:energy:v:339:y:2025:i:c:s0360544225047206. See general information about how to correct material in RePEc.

    If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item. It also allows you to accept potential citations to this item that we are uncertain about.

    If CitEc recognized a bibliographic reference but did not link an item in RePEc to it, you can help with this form .

    If you know of missing items citing this one, you can help us creating those links by adding the relevant references in the same way as above, for each refering item. If you are a registered author of this item, you may also want to check the "citations" tab in your RePEc Author Service profile, as there may be some citations waiting for confirmation.

    For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: Catherine Liu (email available below). General contact details of provider: http://www.journals.elsevier.com/energy .

    Please note that corrections may take a couple of weeks to filter through the various RePEc services.

    IDEAS is a RePEc service. RePEc uses bibliographic data supplied by the respective publishers.