IDEAS home Printed from https://ideas.repec.org/a/eee/appene/v415y2026ics0306261926005143.html

An efficient spatial-temporal graph latent diffusion model for regional ultra-short-term wind speed probabilistic forecasting

Author

Listed:
  • Ma, Long
  • Ping, Jian
  • Li, Yiyan
  • Chen, Sijie
  • Yan, Zheng
  • Ren, Xijun

Abstract

Accurate and efficient regional ultra-short-term wind speed probabilistic forecasting is critical for the integration of renewable energy into power grids, which requires the rapid generation of high-precision forecasts within a short period. Diffusion models excel at learning complex data distributions, making them ideally suited for representing the highly stochastic and fluctuating nature of wind speed. However, their slow, iterative sampling process creates a fundamental bottleneck for time-sensitive forecasting applications. To address this, we propose an efficient spatial-temporal graph latent diffusion model (STGLD), which introduces a novel leap-refine sampling framework to achieve both precision and speed. A leap predictor accelerates sampling by jumping to a coarse intermediate state in one step. Subsequently, a refine denoiser governed by a dynamically scheduled sparse attention mechanism performs efficient and progressive denoising, evolving its receptive field from global to local spatial-temporal patterns. This pipeline operates in a latent space, facilitated by an integrated auto-encoder that reduces the computational burden through dimensionality reduction. Experiments conducted on publicly available wind speed data demonstrate the superiority of our approach. Specifically, STGLD reduces the continuous ranked probability score (CRPS) by at least 3.05% compared to all benchmark models. Furthermore, it achieves a 75% reduction in computational cost while improving reliability by 14.5% and narrowing the prediction interval width by 18.2% compared to other diffusion models.

Suggested Citation

  • Ma, Long & Ping, Jian & Li, Yiyan & Chen, Sijie & Yan, Zheng & Ren, Xijun, 2026. "An efficient spatial-temporal graph latent diffusion model for regional ultra-short-term wind speed probabilistic forecasting," Applied Energy, Elsevier, vol. 415(C).
  • Handle: RePEc:eee:appene:v:415:y:2026:i:c:s0306261926005143
    DOI: 10.1016/j.apenergy.2026.127862
    as

    Download full text from publisher

    File URL: http://www.sciencedirect.com/science/article/pii/S0306261926005143
    Download Restriction: Full text may be restricted for ScienceDirect subscribers

    File URL: https://libkey.io/10.1016/j.apenergy.2026.127862?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. Wang, Jujie & Liu, Yafen & Li, Yaning, 2024. "A parallel differential learning ensemble framework based on enhanced feature extraction and anti-information leakage mechanism for ultra-short-term wind speed forecast," Applied Energy, Elsevier, vol. 361(C).
    2. Draxl, Caroline & Clifton, Andrew & Hodge, Bri-Mathias & McCaa, Jim, 2015. "The Wind Integration National Dataset (WIND) Toolkit," Applied Energy, Elsevier, vol. 151(C), pages 355-366.
    3. Xiong, Zhanhang & Yao, Jianjiang & Huang, Yongmin & Yu, Zhaoxu & Liu, Yalei, 2024. "A wind speed forecasting method based on EMD-MGM with switching QR loss function and novel subsequence superposition," Applied Energy, Elsevier, vol. 353(PB).
    4. Liu, Yongqi & Qin, Hui & Zhang, Zhendong & Pei, Shaoqian & Jiang, Zhiqiang & Feng, Zhongkai & Zhou, Jianzhong, 2020. "Probabilistic spatiotemporal wind speed forecasting based on a variational Bayesian deep learning model," Applied Energy, Elsevier, vol. 260(C).
    5. Hu, Jianming & Heng, Jiani & Wen, Jiemei & Zhao, Weigang, 2020. "Deterministic and probabilistic wind speed forecasting with de-noising-reconstruction strategy and quantile regression based algorithm," Renewable Energy, Elsevier, vol. 162(C), pages 1208-1226.
    6. Baggio, Roberta & Muzy, Jean-François, 2024. "Improving probabilistic wind speed forecasting using M-Rice distribution and spatial data integration," Applied Energy, Elsevier, vol. 360(C).
    7. Yu, Chuanjin & Li, Yongle & Chen, Qian & Lai, Xiaopan & Zhao, Liyang, 2022. "Matrix-based wavelet transformation embedded in recurrent neural networks for wind speed prediction," Applied Energy, Elsevier, vol. 324(C).
    8. Ma, Long & Huang, Ling & Shi, Huifeng, 2023. "A novel spatial–temporal generative autoencoder for wind speed uncertainty forecasting," Energy, Elsevier, vol. 282(C).
    9. 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).
    10. Wang, Jianzhou & Wang, Shuai & Zeng, Bo & Lu, Haiyan, 2022. "A novel ensemble probabilistic forecasting system for uncertainty in wind speed," Applied Energy, Elsevier, vol. 313(C).
    11. Wang, Yun & Xu, Houhua & Song, Mengmeng & Zhang, Fan & Li, Yifen & Zhou, Shengchao & Zhang, Lingjun, 2023. "A convolutional Transformer-based truncated Gaussian density network with data denoising for wind speed forecasting," Applied Energy, Elsevier, vol. 333(C).
    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. Xing, Qianyi & Huang, Xiaojia & Wang, Kang & Wang, Jianzhou & Wang, Shuai, 2025. "MIG-EWPFS: An ensemble probabilistic wind speed forecasting system integrating multi-dimensional feature extraction, hybrid quantile regression, and Knee improved multi-objective optimization," Energy, Elsevier, vol. 324(C).
    2. Wang, Yun & Zhang, Fan & Kou, Hongbo & Zou, Runmin & Hu, Qinghua & Wang, Jianzhou & Srinivasan, Dipti, 2025. "A review of predictive uncertainty modeling techniques and evaluation metrics in probabilistic wind speed and wind power forecasting," Applied Energy, Elsevier, vol. 396(C).
    3. Liu, Xingdou & Zhang, Li & Wang, Jiangong & Zhou, Yue & Gan, Wei, 2023. "A unified multi-step wind speed forecasting framework based on numerical weather prediction grids and wind farm monitoring data," Renewable Energy, Elsevier, vol. 211(C), pages 948-963.
    4. Wang, Yun & Duan, Xiaocong & Zhang, Fan & Wu, Guang & Zou, Runmin & Wan, Jie & Hu, Qinghua, 2025. "MFFDM-WLS: A multi-granularity feature-based coherent forecasting method for temporal hierarchical wind speed time series," Applied Energy, Elsevier, vol. 400(C).
    5. Wang, Yun & Xu, Houhua & Song, Mengmeng & Zhang, Fan & Li, Yifen & Zhou, Shengchao & Zhang, Lingjun, 2023. "A convolutional Transformer-based truncated Gaussian density network with data denoising for wind speed forecasting," Applied Energy, Elsevier, vol. 333(C).
    6. Wang, Ying & Li, Hongmin & Jahanger, Atif & Li, Qiwei & Wang, Biao & Balsalobre-Lorente, Daniel, 2024. "A novel ensemble electricity load forecasting system based on a decomposition-selection-optimization strategy," Energy, Elsevier, vol. 312(C).
    7. 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).
    8. Wang, Chao & Lin, Hong & Yang, Ming & Fu, Xiaoling & Yuan, Yue & Wang, Zewei, 2024. "A novel chaotic time series wind power point and interval prediction method based on data denoising strategy and improved coati optimization algorithm," Chaos, Solitons & Fractals, Elsevier, vol. 187(C).
    9. Tavakol Aghaei, Vahid & Ağababaoğlu, Arda & Bawo, Biram & Naseradinmousavi, Peiman & Yıldırım, Sinan & Yeşilyurt, Serhat & Onat, Ahmet, 2023. "Energy optimization of wind turbines via a neural control policy based on reinforcement learning Markov chain Monte Carlo algorithm," Applied Energy, Elsevier, vol. 341(C).
    10. 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).
    11. Zhang, Yagang & Zhao, Yunpeng & Shen, Xiaoyu & Zhang, Jinghui, 2022. "A comprehensive wind speed prediction system based on Monte Carlo and artificial intelligence algorithms," Applied Energy, Elsevier, vol. 305(C).
    12. Heng, Jiani & Hong, Yongmiao & Hu, Jianming & Wang, Shouyang, 2022. "Probabilistic and deterministic wind speed forecasting based on non-parametric approaches and wind characteristics information," Applied Energy, Elsevier, vol. 306(PA).
    13. Shengcai Zhang & Changsheng Zhu & Xiuting Guo, 2024. "Wind-Speed Multi-Step Forecasting Based on Variational Mode Decomposition, Temporal Convolutional Network, and Transformer Model," Energies, MDPI, vol. 17(9), pages 1-22, April.
    14. Ana Lagos & Joaquín E. Caicedo & Gustavo Coria & Andrés Romero Quete & Maximiliano Martínez & Gastón Suvire & Jesús Riquelme, 2022. "State-of-the-Art Using Bibliometric Analysis of Wind-Speed and -Power Forecasting Methods Applied in Power Systems," Energies, MDPI, vol. 15(18), pages 1-40, September.
    15. Yang, Zhixin & Che, Jinxing, 2025. "A two stage feature extraction and synchronized feature–parameter learning framework for reliable multistep wind speed forecasting," Energy, Elsevier, vol. 340(C).
    16. 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).
    17. Li, Dong & Feng, Yiran & Yan, Xiaoyu, 2026. "An integrated prediction framework combining variational mode optimization decomposition, empirical quantile regression, and QLattice for dynamic point and interval prediction of carbon prices," Energy, Elsevier, vol. 348(C).
    18. Wang Xinxin & Shen Xiaopan & Ai Xueyi & Li Shijia, 2023. "Short-term wind speed forecasting based on a hybrid model of ICEEMDAN, MFE, LSTM and informer," PLOS ONE, Public Library of Science, vol. 18(9), pages 1-27, September.
    19. Gao, Huanxiang & Hu, Gang & Zhang, Dongqin & Jiang, Wenjun & Ren, Hehe & Chen, Wenli, 2024. "Prediction of wind fields in mountains at multiple elevations using deep learning models," Applied Energy, Elsevier, vol. 353(PA).
    20. Wu, Tangjie & Ling, Qiang, 2024. "STELLM: Spatio-temporal enhanced pre-trained large language model for wind speed forecasting," Applied Energy, Elsevier, vol. 375(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:appene:v:415:y:2026:i:c:s0306261926005143. 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.elsevier.com/wps/find/journaldescription.cws_home/405891/description#description .

    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.