IDEAS home Printed from https://ideas.repec.org/a/eee/appene/v405y2026ics0306261925019397.html

Missing data-aware robust electrical load forecasting based on hierarchical downsampling-upsampling spatiotemporal graph network

Author

Listed:
  • Zhao, Pengfei
  • Shen, Zhirong
  • Cao, Di
  • Lin, Zhiping
  • Chen, Zhe
  • Hu, Weihao

Abstract

In real-world power systems, missing data is a frequent and inevitable issue due to sensor malfunctions and data transmission errors. This poses huge challenges for electrical load forecasting tasks since incomplete data can disrupt temporal patterns and obscure spatial dependencies. Traditional forecasting methods usually address this by imputing missing values before prediction, but such preprocessing can introduce bias and lead to error accumulation. To this end, this paper proposes a novel end-to-end missing data-oriented load forecasting framework based on the hierarchical downsampling-upsampling spatiotemporal graph network (HDU-STGNN). The proposed method can directly predict future load demand from partially observed inputs without requiring any data imputation process. Specifically, a temporal downsampling module is first developed to summarize observed portions of the input sequence into coarse-to-fine representations. This allows the model to capture long- and short-term load patterns while reducing sensitivity to irregularly missing entries. Then, a spatial coarsening and upsampling mechanism is proposed for effective information propagation across distant nodes. This allows the model to recover spatial dependencies even when local observations are unavailable. Finally, a multi-resolution attention fusion layer is utilized to adaptively reweight spatiotemporal features, which helps the model focus on reliable signals and suppress noise caused by incomplete data. Extensive experiments on real-world load datasets, covering three aggregation levels and missing rates up to 90 %, demonstrate the robustness of HDU-STGNN under varying degrees of data sparsity. In particular, the proposed model achieves an average reduction of 6.7 % in MAE and 9.9 % in MAPE compared with the strongest baseline across all settings, with improvements reaching up to 17.4 % under high missingness conditions.

Suggested Citation

  • Zhao, Pengfei & Shen, Zhirong & Cao, Di & Lin, Zhiping & Chen, Zhe & Hu, Weihao, 2026. "Missing data-aware robust electrical load forecasting based on hierarchical downsampling-upsampling spatiotemporal graph network," Applied Energy, Elsevier, vol. 405(C).
    • Handle: RePEc:eee:appene:v:405:y:2026:i:c:s0306261925019397
    DOI: 10.1016/j.apenergy.2025.127209
    as

    Download full text from publisher

    File URL: http://www.sciencedirect.com/science/article/pii/S0306261925019397
    Download Restriction: Full text for ScienceDirect subscribers only
    File URL: https://libkey.io/10.1016/j.apenergy.2025.127209?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. Wen, Honglin, 2024. "Probabilistic wind power forecasting resilient to missing values: An adaptive quantile regression approach," Energy, Elsevier, vol. 300(C).
    2. Saini, Priyesh & Parida, S.K., 2024. "A novel probabilistic gradient boosting model with multi-approach feature selection and iterative seasonal trend decomposition for short-term load forecasting," Energy, Elsevier, vol. 294(C).
    3. Deng, Song & Dong, Xia & Tao, Li & Wang, Junjie & He, Yi & Yue, Dong, 2024. "Multi-type load forecasting model based on random forest and density clustering with the influence of noise and load patterns," Energy, Elsevier, vol. 307(C).
    4. Ben Taieb, Souhaib & Hyndman, Rob J., 2014. "A gradient boosting approach to the Kaggle load forecasting competition," International Journal of Forecasting, Elsevier, vol. 30(2), pages 382-394.
    5. Hahn, Heiko & Meyer-Nieberg, Silja & Pickl, Stefan, 2009. "Electric load forecasting methods: Tools for decision making," European Journal of Operational Research, Elsevier, vol. 199(3), pages 902-907, December.
    6. Gao, Mingyang & Zhou, Suyang & Gu, Wei & Wu, Zhi & Liu, Haiquan & Zhou, Aihua & Wang, Xinliang, 2025. "MMGPT4LF: Leveraging an optimized pre-trained GPT-2 model with multi-modal cross-attention for load forecasting," Applied Energy, Elsevier, vol. 392(C).
    7. Zhang, Luliang & Jiang, Zongxi & Ji, Tianyao & Chen, Ziming, 2025. "Diffusion-based inpainting approach for multifunctional short-term load forecasting," Applied Energy, Elsevier, vol. 377(PB).
    8. Tian, Zhirui & Liu, Weican & Jiang, Wenqian & Wu, Chenye, 2024. "CNNs-Transformer based day-ahead probabilistic load forecasting for weekends with limited data availability," Energy, Elsevier, vol. 293(C).
    9. Imani, Maryam, 2021. "Electrical load-temperature CNN for residential load forecasting," Energy, Elsevier, vol. 227(C).
    10. Dai, Yeming & Zhao, Pei, 2020. "A hybrid load forecasting model based on support vector machine with intelligent methods for feature selection and parameter optimization," Applied Energy, Elsevier, vol. 279(C).
    11. Zhu, Jizhong & Dong, Hanjiang & Zheng, Weiye & Li, Shenglin & Huang, Yanting & Xi, Lei, 2022. "Review and prospect of data-driven techniques for load forecasting in integrated energy systems," Applied Energy, Elsevier, vol. 321(C).
    12. Li, Chuang & Li, Guojie & Wang, Keyou & Han, Bei, 2022. "A multi-energy load forecasting method based on parallel architecture CNN-GRU and transfer learning for data deficient integrated energy systems," Energy, Elsevier, vol. 259(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. Wang, Danhao & Peng, Daogang & Huang, Dongmei & Zhao, Huirong & Qu, Bogang, 2025. "MMEMformer: A multi-scale memory-enhanced transformer framework for short-term load forecasting in integrated energy systems," Energy, Elsevier, vol. 322(C).
    2. Hu, Rong & Zhou, Kaile & Lu, Xinhui, 2025. "Integrated loads forecasting with absence of crucial factors," Energy, Elsevier, vol. 322(C).
    3. Liu, Tianhao & Li, Fangning & Zhang, Dongdong & Shan, Linke & Zhu, Hongyu & Du, Pengcheng & Jiang, Meihui & Goh, Hui Hwang & Kurniawan, Tonni Agustiono & Huang, Chao & Kong, Fannie, 2026. "Intelligent load forecasting technologies for diverse scenarios in the new power systems," Renewable and Sustainable Energy Reviews, Elsevier, vol. 226(PD).
    4. Fan, Jingmin & Zhong, Mingwei & Guan, Yuanpeng & Yi, Siqi & Xu, Cancheng & Zhai, Yanpeng & Zhou, Yongwang, 2024. "An online long-term load forecasting method: Hierarchical highway network based on crisscross feature collaboration," Energy, Elsevier, vol. 299(C).
    5. Yin, Linfei & Ju, Linyi, 2025. "ShuffleTransformerMulti-headAttentionNet network for user load forecasting," Energy, Elsevier, vol. 322(C).
    6. Xie, Xiangmin & Ding, Yuhao & Sun, Yuanyuan & Zhang, Zhisheng & Fan, Jianhua, 2024. "A novel time-series probabilistic forecasting method for multi-energy loads," Energy, Elsevier, vol. 306(C).
    7. Ren, Xiaoxiao & Tian, Xin & Wang, Kai & Yang, Sifan & Chen, Weixiong & Wang, Jinshi, 2025. "Enhanced load forecasting for distributed multi-energy system: A stacking ensemble learning method with deep reinforcement learning and model fusion," Energy, Elsevier, vol. 319(C).
    8. Zhao, Xiaoyu & Duan, Pengfei & Cao, Xiaodong & Xue, Qingwen & Zhao, Bingxu & Hu, Jinxue & Zhang, Chenyang & Yuan, Xiaoyang, 2025. "A probabilistic load forecasting method for multi-energy loads based on inflection point optimization and integrated feature screening," Energy, Elsevier, vol. 327(C).
    9. Xu, Huifeng & Hu, Feihu & Liang, Xinhao & Zhao, Guoqing & Abugunmi, Mohammad, 2024. "A framework for electricity load forecasting based on attention mechanism time series depthwise separable convolutional neural network," Energy, Elsevier, vol. 299(C).
    10. Semmelmann, Leo & Hertel, Matthias & Kircher, Kevin J. & Mikut, Ralf & Hagenmeyer, Veit & Weinhardt, Christof, 2024. "The impact of heat pumps on day-ahead energy community load forecasting," Applied Energy, Elsevier, vol. 368(C).
    11. Li, Ke & Qin, Zheng & Mu, Yuchen & Wang, Haiyang & Bie, Qingfeng & Yin, Xianxin & Yan, Yi, 2025. "Transfer learning-based multi-energy load forecasting method for integrated energy system with zero-shot," Applied Energy, Elsevier, vol. 401(PC).
    12. Yan, Qin & Lu, Zhiying & Liu, Hong & He, Xingtang & Zhang, Xihai & Guo, Jianlin, 2024. "Short-term prediction of integrated energy load aggregation using a bi-directional simple recurrent unit network with feature-temporal attention mechanism ensemble learning model," Applied Energy, Elsevier, vol. 355(C).
    13. Samuel Atuahene & Yukun Bao & Patricia Semwaah Gyan & Yao Yevenyo Ziggah, 2019. "Accurate Forecast Improvement Approach for Short Term Load Forecasting Using Hybrid Filter-Wrap Feature Selection," International Journal of Management Science and Business Administration, Inovatus Services Ltd., vol. 5(2), pages 37-49, January.
    14. Ma, Xin & Peng, Bo & Ma, Xiangxue & Tian, Changbin & Yan, Yi, 2023. "Multi-timescale optimization scheduling of regional integrated energy system based on source-load joint forecasting," Energy, Elsevier, vol. 283(C).
    15. Chen, Wenhao & Rong, Fei & Lin, Chuan, 2025. "A multi-energy loads forecasting model based on dual attention mechanism and multi-scale hierarchical residual network with gated recurrent unit," Energy, Elsevier, vol. 320(C).
    16. Xue, Kai & Wang, Jinshi & He, Maoen & Zhao, Quanbin & Islam, M.R. & Chua, K.J., 2025. "Joint dispatch and economic collaboration of multiple regional energy systems via Transformer-based load prediction and two-stage stochastic optimization," Energy, Elsevier, vol. 333(C).
    17. Li, Ke & Mu, Yuchen & Yang, Fan & Wang, Haiyang & Yan, Yi & Zhang, Chenghui, 2023. "A novel short-term multi-energy load forecasting method for integrated energy system based on feature separation-fusion technology and improved CNN," Applied Energy, Elsevier, vol. 351(C).
    18. Guo, Xifeng & Liu, Rongqian & Wang, Yonggang & Ning, Yi & Qu, Qiuxia & Wang, Zedi & Cong, Wenzhuo, 2025. "Short-term power load forecasting for estate-level buildings considering multilevel feature extraction and adaptive fusion," Energy, Elsevier, vol. 337(C).
    19. Jian Liu & Xiaotian He & Kangji Li & Wenping Xue, 2025. "A Review of State-of-the-Art AI and Data-Driven Techniques for Load Forecasting," Energies, MDPI, vol. 18(16), pages 1-27, August.
    20. Hu, Zhongyi & Bao, Yukun & Chiong, Raymond & Xiong, Tao, 2015. "Mid-term interval load forecasting using multi-output support vector regression with a memetic algorithm for feature selection," Energy, Elsevier, vol. 84(C), pages 419-431.

    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:405:y:2026:i:c:s0306261925019397. 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.