IDEAS home Printed from https://ideas.repec.org/a/eee/energy/v347y2026ics0360544226004974.html

Offshore Wind farm cluster power forecasting: An ASTGCN framework with dual-layer Co-evolution of loss function and graph construction method

Author

Listed:
  • Xiao, Liexi
  • Meng, Anbo
  • Zhang, Qi
  • Song, Shihao
  • Yin, Hao
  • Luo, Jianqiang

Abstract

Graph neural networks show potential in offshore wind farm cluster power output forecasting, but are limited by two challenges: adaptive loss function selection across different wind farm groups and optimal graph structure construction under dynamic wind speed propagation. Traditional methods use fixed loss functions and static graphs, failing to capture spatiotemporal coupling and nonlinear power mapping, leading to subpar accuracy in complex environments. This paper proposes a novel Loss–Construction Dual-layer Co-evolution Framework (LCDCE) based on ASTGCN. The core of LCDCE is a synergistic evolution mechanism that dynamically couples the evolution of loss functions and graph construction strategies, enabling adaptive and joint optimization of the objective landscape and spatial-temporal dependencies. A global optimal model selection mechanism ensures generalizability, and a cosine annealing scheduler balances convergence speed and optimization. Experiments on real European offshore wind farm data show the framework reduces RMSE by 33.46% and MAE by 17.02% compared to conventional ASTGCN, proving the dual-layer strategy adapts to complex wind farm cluster for robust forecasting.

Suggested Citation

  • Xiao, Liexi & Meng, Anbo & Zhang, Qi & Song, Shihao & Yin, Hao & Luo, Jianqiang, 2026. "Offshore Wind farm cluster power forecasting: An ASTGCN framework with dual-layer Co-evolution of loss function and graph construction method," Energy, Elsevier, vol. 347(C).
    • Handle: RePEc:eee:energy:v:347:y:2026:i:c:s0360544226004974
    DOI: 10.1016/j.energy.2026.140394
    as

    Download full text from publisher

    File URL: http://www.sciencedirect.com/science/article/pii/S0360544226004974
    Download Restriction: Full text for ScienceDirect subscribers only
    File URL: https://libkey.io/10.1016/j.energy.2026.140394?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. Chen, Juntao & Fu, Xueying & Zhang, Lingli & Shen, Haoye & Wu, Jibo, 2024. "A novel offshore wind power prediction model based on TCN-DANet-sparse transformer and considering spatio-temporal coupling in multiple wind farms," Energy, Elsevier, vol. 308(C).
    2. Du, Ruoyun & Chen, Hongfei & Yu, Min & Li, Wanying & Niu, Dongxiao & Wang, Keke & Zhang, Zuozhong, 2024. "3DTCN-CBAM-LSTM short-term power multi-step prediction model for offshore wind power based on data space and multi-field cluster spatio-temporal correlation," Applied Energy, Elsevier, vol. 376(PA).
    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. Wang, Chen & Zhou, Dengji & Wang, Xiaoguo & Liu, Song & Shao, Tiemin & Shui, Chongyuan & Yan, Jun, 2024. "Multiscale graph based spatio-temporal graph convolutional network for energy consumption prediction of natural gas transmission process," Energy, Elsevier, vol. 307(C).
    5. Meng, Anbo & Zhang, Haitao & Dai, Zhongfu & Xian, Zikang & Xiao, Liexi & Rong, Jiayu & Li, Chen & Zhu, Jianbin & Li, Hanhong & Yin, Yiding & Liu, Jiawei & Tang, Yanshu & Zhang, Bin & Yin, Hao, 2024. "An adaptive distribution-matched recurrent network for wind power prediction using time-series distribution period division," Energy, Elsevier, vol. 299(C).
    6. Meng, Anbo & Zhang, Haitao & Yin, Hao & Xian, Zikang & Chen, Shu & Zhu, Zibin & Zhang, Zheng & Rong, Jiayu & Li, Chen & Wang, Chenen & Wu, Zhenbo & Deng, Weisi & Luo, Jianqiang & Wang, Xiaolin, 2023. "A novel multi-gradient evolutionary deep learning approach for few-shot wind power prediction using time-series GAN," Energy, Elsevier, vol. 283(C).
    7. 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).
    8. Wang, Zhongrui & Wang, Chunbo & Chen, Liang & Yu, Min & Yuan, Wenteng, 2025. "Short-term offshore wind power multi-location multi-modal multi-step prediction model based on Informer (M3STIN)," Energy, Elsevier, vol. 322(C).
    9. Jin, Huaiping & Zhang, Kehao & Fan, Shouyuan & Jin, Huaikang & Wang, Bin, 2024. "Wind power forecasting based on ensemble deep learning with surrogate-assisted evolutionary neural architecture search and many-objective federated learning," Energy, Elsevier, vol. 308(C).
    10. Qu, Zhijian & Li, Jian & Hou, Xinxing & Gui, Jianglin, 2023. "A D-stacking dual-fusion, spatio-temporal graph deep neural network based on a multi-integrated overlay for short-term wind-farm cluster power multi-step prediction," Energy, Elsevier, vol. 281(C).
    11. Oliver Grothe & Fabian Kächele & Mira Watermeyer, 2022. "Analyzing Europe’s Biggest Offshore Wind Farms: A Data Set with 40 Years of Hourly Wind Speeds and Electricity Production," Energies, MDPI, vol. 15(5), pages 1-24, February.
    12. Yin, Hao & Li, Chen & Chen, Shuxuan & Meng, Anbo, 2025. "Few-shot wind power prediction using sample transfer and imbalanced evolved neural network," Energy, Elsevier, vol. 328(C).
    13. Zhuang, Yingrui & Cheng, Lin & Qi, Ning & Wang, Xinyi & Chen, Yue, 2025. "Real-time hosting capacity assessment for electric vehicles: A sequential forecast-then-optimize method," Applied Energy, Elsevier, vol. 380(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. Xiao, Liexi & Wang, Yu & Meng, Anbo & Tan, Zhenglin & Chen, Shuxuan & Song, Shihao & Yin, Hao & Luo, Jianqiang, 2025. "Power prediction methods for offshore wind farm clusters: interpretable ASTGCN based on wind speed delay perception and spatial feature fusion," Energy, Elsevier, vol. 341(C).
    2. Song, Shihao & Meng, Anbo & Tan, Zhenglin & Lu, Jiajun & Xiao, Liexi & Yin, Hao & Luo, Jianqiang, 2026. "Dynamic graph convolutional network considering wind speed delay and two-stage transfer learning applied to few-shot wind power prediction," Energy, Elsevier, vol. 342(C).
    3. Chen, Juntao & Fu, Xueying & Zhang, Lingli & Shen, Haoye & Wu, Jibo, 2024. "A novel offshore wind power prediction model based on TCN-DANet-sparse transformer and considering spatio-temporal coupling in multiple wind farms," Energy, Elsevier, vol. 308(C).
    4. Qu, Zhijian & Hou, Xinxing & Li, Jian & Hu, Wenbo, 2024. "Short-term wind farm cluster power prediction based on dual feature extraction and quadratic decomposition aggregation," Energy, Elsevier, vol. 290(C).
    5. Qu, Zhijian & Hou, Xinxing & Huang, ShiXun & Li, Di & He, Yang & Meng, Yan, 2025. "Probabilistic power forecasting for wind farm clusters using Moran-Graph network with posterior feedback attention mechanism," Energy, Elsevier, vol. 328(C).
    6. Yang, Mao & Han, Chao & Zhang, Wei & Wang, Bo, 2024. "A short-term power prediction method for wind farm cluster based on the fusion of multi-source spatiotemporal feature information," Energy, Elsevier, vol. 294(C).
    7. Yang, Mao & Jiang, Yuxi & Xu, Chuanyu & Wang, Bo & Wang, Zhao & Su, Xin, 2025. "Day-ahead wind farm cluster power prediction based on trend categorization and spatial information integration model," Applied Energy, Elsevier, vol. 388(C).
    8. Cui, Xiwen & Yu, Xiaoyu & Niu, Haowei & Niu, Dongxiao & Liu, Da, 2025. "A novel data-driven multi-step wind power point-interval prediction framework integrating sliding window-based two-layer adaptive decomposition and multi-objective optimization for balancing prediction accuracy and stability," Applied Energy, Elsevier, vol. 397(C).
    9. Li, HongYang & He, Shan & Yuan, JiaWang & Wang, Chao, 2025. "A wind power prediction method integrating dynamic multi-scale spatio-temporal modelling, adaptive multi-strategy local decomposition, and meta-learning ensemble model," Energy, Elsevier, vol. 340(C).
    10. Ma, Tingxia & Wang, Tengzan & Wang, Lin & Tan, Jianying & Cao, Yujiao & Guo, Junyu, 2025. "A hybrid deep learning model towards flow pattern identification of gas-liquid two-phase flows in horizontal pipe," Energy, Elsevier, vol. 320(C).
    11. López-Franca, Noelia & Gaertner, Miguel Ángel & Sánchez, Enrique & Gutiérrez, Claudia & Ortega, María & Gallardo, Clemente, 2026. "Offshore wind energy in the Iberian Peninsula: A comparative analysis of availability, persistence, and complementarity with onshore wind and solar photovoltaic generation," Renewable Energy, Elsevier, vol. 258(C).
    12. Gang Li & Chen Lin & Yupeng Li, 2025. "Probabilistic Forecasting of Provincial Regional Wind Power Considering Spatio-Temporal Features," Energies, MDPI, vol. 18(3), pages 1-17, January.
    13. Li, Jianfang & Jia, Li & Zhou, Chengyu, 2024. "Probability density function based adaptive ensemble learning with global convergence for wind power prediction," Energy, Elsevier, vol. 312(C).
    14. Yang, Mao & Guo, Yunfeng & Huang, Tao & Fan, Fulin & Ma, Chenglian & Fang, Guozhong, 2024. "Wind farm cluster power prediction based on graph deviation attention network with learnable graph structure and dynamic error correction during load peak and valley periods," Energy, Elsevier, vol. 312(C).
    15. Xue, Xiaorui & Li, Shaofang & Wang, Xiaonan & Ren, Tingting, 2026. "Enhancing stock market predictions with multivariate signal decomposition and dynamic feature optimization," The North American Journal of Economics and Finance, Elsevier, vol. 81(C).
    16. He Yin & Hai Lan & Ying-Yi Hong & Zhuangwei Wang & Peng Cheng & Dan Li & Dong Guo, 2023. "A Comprehensive Review of Shipboard Power Systems with New Energy Sources," Energies, MDPI, vol. 16(5), pages 1-44, February.
    17. Wei Du & Shi-Tao Peng & Pei-Sen Wu & Ming-Lang Tseng, 2024. "High-Accuracy Photovoltaic Power Prediction under Varying Meteorological Conditions: Enhanced and Improved Beluga Whale Optimization Extreme Learning Machine," Energies, MDPI, vol. 17(10), pages 1-21, May.
    18. 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).
    19. Liu, Jiarui & Fu, Yuchen, 2023. "Renewable energy forecasting: A self-supervised learning-based transformer variant," Energy, Elsevier, vol. 284(C).
    20. Liu, Tianhao & Shan, Linke & Jiang, Meihui & Li, Fangning & Kong, Fannie & Du, Pengcheng & Zhu, Hongyu & Goh, Hui Hwang & Kurniawan, Tonni Agustiono & Huang, Chao & Zhang, Dongdong, 2025. "Multi-dimensional data processing and intelligent forecasting technologies for renewable energy generation," Applied Energy, Elsevier, vol. 398(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:347:y:2026:i:c:s0360544226004974. 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.