IDEAS home Printed from https://ideas.repec.org/a/eee/appene/v333y2023ics0306261922018220.html
   My bibliography  Save this article

Spatio-temporal wind speed forecasting using graph networks and novel Transformer architectures

Author

Listed:
  • Bentsen, Lars Ødegaard
  • Warakagoda, Narada Dilp
  • Stenbro, Roy
  • Engelstad, Paal

Abstract

To improve the security and reliability of wind energy production, short-term forecasting has become of utmost importance. This study focuses on multi-step spatio-temporal wind speed forecasting for the Norwegian continental shelf. In particular, the study considers 14 offshore measurement stations and aims to leverage spatial dependencies through the relative physical location of different stations to improve local wind forecasts and simultaneously output different forecasts for each of the 14 locations. Our multi-step forecasting models produce either 10-minute, 1- or 4-hour forecasts, with 10-minute resolution, meaning that the models produce more informative time series for predicted future trends. A graph neural network (GNN) architecture was used to extract spatial dependencies, with different update functions to learn temporal correlations. These update functions were implemented using different neural network architectures. One such architecture, the Transformer, has become increasingly popular for sequence modelling in recent years. Various alterations have been proposed to better facilitate time series forecasting, of which this study focused on the Informer, LogSparse Transformer and Autoformer. This is the first time the LogSparse Transformer and Autoformer have been applied to wind forecasting and the first time any of these or the Informer have been formulated in a spatio-temporal setting for wind forecasting. By comparing against spatio-temporal Long Short-Term Memory (LSTM) and Multi-Layer Perceptron (MLP) models, the study showed that the models using the altered Transformer architectures as update functions in GNNs were able to outperform these. Furthermore, we propose the Fast Fourier Transformer (FFTransformer), which is a novel Transformer architecture based on signal decomposition and consists of two separate streams that analyse the trend and periodic components separately. The FFTransformer and Autoformer were found to achieve superior results for the 10-minute and 1-hour ahead forecasts, with the FFTransformer significantly outperforming all other models for the 4-hour ahead forecasts. Our code to implement the different models are made publicly available at: https://github.com/LarsBentsen/FFTransformer.

Suggested Citation

  • Bentsen, Lars Ødegaard & Warakagoda, Narada Dilp & Stenbro, Roy & Engelstad, Paal, 2023. "Spatio-temporal wind speed forecasting using graph networks and novel Transformer architectures," Applied Energy, Elsevier, vol. 333(C).
    • Handle: RePEc:eee:appene:v:333:y:2023:i:c:s0306261922018220
    DOI: 10.1016/j.apenergy.2022.120565
    as

    Download full text from publisher

    File URL: http://www.sciencedirect.com/science/article/pii/S0306261922018220
    Download Restriction: Full text for ScienceDirect subscribers only
    File URL: https://libkey.io/10.1016/j.apenergy.2022.120565?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 search for a different version of it.

    References listed on IDEAS

    as
    1. Wang, H.Z. & Wang, G.B. & Li, G.Q. & Peng, J.C. & Liu, Y.T., 2016. "Deep belief network based deterministic and probabilistic wind speed forecasting approach," Applied Energy, Elsevier, vol. 182(C), pages 80-93.
    2. Sfetsos, A., 2002. "A novel approach for the forecasting of mean hourly wind speed time series," Renewable Energy, Elsevier, vol. 27(2), pages 163-174.
    3. Colak, Ilhami & Sagiroglu, Seref & Yesilbudak, Mehmet, 2012. "Data mining and wind power prediction: A literature review," Renewable Energy, Elsevier, vol. 46(C), pages 241-247.
    4. Shi, Jing & Guo, Jinmei & Zheng, Songtao, 2012. "Evaluation of hybrid forecasting approaches for wind speed and power generation time series," Renewable and Sustainable Energy Reviews, Elsevier, vol. 16(5), pages 3471-3480.
    5. Pan, Xiaoxin & Wang, Long & Wang, Zhongju & Huang, Chao, 2022. "Short-term wind speed forecasting based on spatial-temporal graph transformer networks," Energy, Elsevier, vol. 253(C).
    6. Wang, Fei & Chen, Peng & Zhen, Zhao & Yin, Rui & Cao, Chunmei & Zhang, Yagang & Duić, Neven, 2022. "Dynamic spatio-temporal correlation and hierarchical directed graph structure based ultra-short-term wind farm cluster power forecasting method," Applied Energy, Elsevier, vol. 323(C).
    7. Kavasseri, Rajesh G. & Seetharaman, Krithika, 2009. "Day-ahead wind speed forecasting using f-ARIMA models," Renewable Energy, Elsevier, vol. 34(5), pages 1388-1393.
    8. Niu, Zhewen & Yu, Zeyuan & Tang, Wenhu & Wu, Qinghua & Reformat, Marek, 2020. "Wind power forecasting using attention-based gated recurrent unit network," Energy, Elsevier, vol. 196(C).
    9. Aasim, & Singh, S.N. & Mohapatra, Abheejeet, 2019. "Repeated wavelet transform based ARIMA model for very short-term wind speed forecasting," Renewable Energy, Elsevier, vol. 136(C), pages 758-768.
    10. Wang, Lei & He, Yigang, 2022. "M2STAN: Multi-modal multi-task spatiotemporal attention network for multi-location ultra-short-term wind power multi-step predictions," Applied Energy, Elsevier, vol. 324(C).
    11. Kumar Shivam & Jong-Chyuan Tzou & Shang-Chen Wu, 2020. "Multi-Step Short-Term Wind Speed Prediction Using a Residual Dilated Causal Convolutional Network with Nonlinear Attention," Energies, MDPI, vol. 13(7), pages 1-29, April.
    12. Lim, Bryan & Arık, Sercan Ö. & Loeff, Nicolas & Pfister, Tomas, 2021. "Temporal Fusion Transformers for interpretable multi-horizon time series forecasting," International Journal of Forecasting, Elsevier, vol. 37(4), pages 1748-1764.
    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. da Silva, Ramon Gomes & Ribeiro, Matheus Henrique Dal Molin & Moreno, Sinvaldo Rodrigues & Mariani, Viviana Cocco & Coelho, Leandro dos Santos, 2021. "A novel decomposition-ensemble learning framework for multi-step ahead wind energy forecasting," Energy, Elsevier, vol. 216(C).
    15. 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).
    16. Putz, Dominik & Gumhalter, Michael & Auer, Hans, 2021. "A novel approach to multi-horizon wind power forecasting based on deep neural architecture," Renewable Energy, Elsevier, vol. 178(C), pages 494-505.
    17. Liu, Hui & Tian, Hong-qi & Pan, Di-fu & Li, Yan-fei, 2013. "Forecasting models for wind speed using wavelet, wavelet packet, time series and Artificial Neural Networks," Applied Energy, Elsevier, vol. 107(C), pages 191-208.
    Full references (including those not matched with items on IDEAS)

    Citations

    Citations are extracted by the CitEc Project, subscribe to its RSS feed for this item.
    as


    Cited by:

    1. Chen, Zhengganzhe & Zhang, Bin & Du, Chenglong & Meng, Wei & Meng, Anbo, 2024. "A novel dynamic spatio-temporal graph convolutional network for wind speed interval prediction," Energy, Elsevier, vol. 294(C).
    2. Wu, Binrong & Wang, Lin, 2024. "Two-stage decomposition and temporal fusion transformers for interpretable wind speed forecasting," Energy, Elsevier, vol. 288(C).
    3. Wu Xu & Wenjing Dai & Dongyang Li & Qingchang Wu, 2024. "Short-Term Wind Power Prediction Based on a Variational Mode Decomposition–BiTCN–Psformer Hybrid Model," Energies, MDPI, vol. 17(16), pages 1-17, August.
    4. Lars Ødegaard Bentsen & Narada Dilp Warakagoda & Roy Stenbro & Paal Engelstad, 2023. "A Unified Graph Formulation for Spatio-Temporal Wind Forecasting," Energies, MDPI, vol. 16(20), pages 1-23, October.
    5. Jiang, Wenjun & Liu, Bo & Liang, Yang & Gao, Huanxiang & Lin, Pengfei & Zhang, Dongqin & Hu, Gang, 2024. "Applicability analysis of transformer to wind speed forecasting by a novel deep learning framework with multiple atmospheric variables," Applied Energy, Elsevier, vol. 353(PB).
    6. 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).
    7. Wang, Shuangxin & Shi, Jiarong & Yang, Wei & Yin, Qingyan, 2024. "High and low frequency wind power prediction based on Transformer and BiGRU-Attention," Energy, Elsevier, vol. 288(C).
    8. Jinhua Zhang & Hui Li & Peng Cheng & Jie Yan, 2024. "Interpretable Wind Power Short-Term Power Prediction Model Using Deep Graph Attention Network," Energies, MDPI, vol. 17(2), pages 1-16, January.
    9. Xian, Sidong & Feng, Miaomiao & Cheng, Yue, 2023. "Incremental nonlinear trend fuzzy granulation for carbon trading time series forecast," Applied Energy, Elsevier, vol. 352(C).
    10. Yang, Ting & Yang, Zhenning & Li, Fei & Wang, Hengyu, 2024. "A short-term wind power forecasting method based on multivariate signal decomposition and variable selection," Applied Energy, Elsevier, vol. 360(C).
    11. Lv, Yunlong & Hu, Qin & Xu, Hang & Lin, Huiyao & Wu, Yufan, 2024. "An ultra-short-term wind power prediction method based on spatial-temporal attention graph convolutional model," Energy, Elsevier, vol. 293(C).
    12. Junhao Zhao & Xiaodong Shen & Youbo Liu & Junyong Liu & Xisheng Tang, 2024. "Enhancing Aggregate Load Forecasting Accuracy with Adversarial Graph Convolutional Imputation Network and Learnable Adjacency Matrix," Energies, MDPI, vol. 17(18), pages 1-28, September.
    13. Hongxia Wang & Xiao Jin & Jianian Wang & Hongxia Hao, 2023. "Nonparametric Estimation for High-Dimensional Space Models Based on a Deep Neural Network," Mathematics, MDPI, vol. 11(18), pages 1-37, September.
    14. Zhu, Nanyang & Wang, Ying & Yuan, Kun & Yan, Jiahao & Li, Yaping & Zhang, Kaifeng, 2024. "GGNet: A novel graph structure for power forecasting in renewable power plants considering temporal lead-lag correlations," Applied Energy, Elsevier, vol. 364(C).
    15. Zhang, Dongqin & Hu, Gang & Song, Jie & Gao, Huanxiang & Ren, Hehe & Chen, Wenli, 2024. "A novel spatio-temporal wind speed forecasting method based on the microscale meteorological model and a hybrid deep learning model," Energy, Elsevier, vol. 288(C).
    16. 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).
    17. Chen, Fuhao & Yan, Jie & Liu, Yongqian & Yan, Yamin & Tjernberg, Lina Bertling, 2024. "A novel meta-learning approach for few-shot short-term wind power forecasting," Applied Energy, Elsevier, vol. 362(C).

    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. Wu, Binrong & Yu, Sihao & Peng, Lu & Wang, Lin, 2024. "Interpretable wind speed forecasting with meteorological feature exploring and two-stage decomposition," Energy, Elsevier, vol. 294(C).
    2. Du, Pei & Yang, Dongchuan & Li, Yanzhao & Wang, Jianzhou, 2024. "An innovative interpretable combined learning model for wind speed forecasting," Applied Energy, Elsevier, vol. 358(C).
    3. 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).
    4. Lars Ødegaard Bentsen & Narada Dilp Warakagoda & Roy Stenbro & Paal Engelstad, 2023. "A Unified Graph Formulation for Spatio-Temporal Wind Forecasting," Energies, MDPI, vol. 16(20), pages 1-23, October.
    5. 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).
    6. 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.
    7. Konstantinos Blazakis & Yiannis Katsigiannis & Georgios Stavrakakis, 2022. "One-Day-Ahead Solar Irradiation and Windspeed Forecasting with Advanced Deep Learning Techniques," Energies, MDPI, vol. 15(12), pages 1-25, June.
    8. 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).
    9. Liu, Chenyu & Zhang, Xuemin & Mei, Shengwei & Zhou, Qingyu & Fan, Hang, 2023. "Series-wise attention network for wind power forecasting considering temporal lag of numerical weather prediction," Applied Energy, Elsevier, vol. 336(C).
    10. Zonggui Yao & Chen Wang, 2018. "A Hybrid Model Based on A Modified Optimization Algorithm and An Artificial Intelligence Algorithm for Short-Term Wind Speed Multi-Step Ahead Forecasting," Sustainability, MDPI, vol. 10(5), pages 1-33, May.
    11. 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).
    12. Nascimento, Erick Giovani Sperandio & de Melo, Talison A.C. & Moreira, Davidson M., 2023. "A transformer-based deep neural network with wavelet transform for forecasting wind speed and wind energy," Energy, Elsevier, vol. 278(C).
    13. Yang, Ting & Yang, Zhenning & Li, Fei & Wang, Hengyu, 2024. "A short-term wind power forecasting method based on multivariate signal decomposition and variable selection," Applied Energy, Elsevier, vol. 360(C).
    14. Lv, Sheng-Xiang & Wang, Lin, 2023. "Multivariate wind speed forecasting based on multi-objective feature selection approach and hybrid deep learning model," Energy, Elsevier, vol. 263(PE).
    15. 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).
    16. Lv, Sheng-Xiang & Wang, Lin, 2022. "Deep learning combined wind speed forecasting with hybrid time series decomposition and multi-objective parameter optimization," Applied Energy, Elsevier, vol. 311(C).
    17. Saeed, Adnan & Li, Chaoshun & Gan, Zhenhao & Xie, Yuying & Liu, Fangjie, 2022. "A simple approach for short-term wind speed interval prediction based on independently recurrent neural networks and error probability distribution," Energy, Elsevier, vol. 238(PC).
    18. Sandra Minerva Valdivia-Bautista & José Antonio Domínguez-Navarro & Marco Pérez-Cisneros & Carlos Jesahel Vega-Gómez & Beatriz Castillo-Téllez, 2023. "Artificial Intelligence in Wind Speed Forecasting: A Review," Energies, MDPI, vol. 16(5), pages 1-28, March.
    19. Luca Di Persio & Nicola Fraccarolo & Andrea Veronese, 2024. "Wind Energy Production in Italy: A Forecasting Approach Based on Fractional Brownian Motion and Generative Adversarial Networks," Mathematics, MDPI, vol. 12(13), pages 1-16, July.
    20. Chengqing, Yu & Guangxi, Yan & Chengming, Yu & Yu, Zhang & Xiwei, Mi, 2023. "A multi-factor driven spatiotemporal wind power prediction model based on ensemble deep graph attention reinforcement learning networks," Energy, Elsevier, vol. 263(PE).

    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:333:y:2023:i:c:s0306261922018220. 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.