IDEAS home Printed from https://ideas.repec.org/a/eee/appene/v364y2024ics0306261924005397.html
   My bibliography  Save this article

Self-learning dynamic graph neural network with self-attention based on historical data and future data for multi-task multivariate residential air conditioning forecasting

Author

Listed:
  • Hu, Zehuan
  • Gao, Yuan
  • Sun, Luning
  • Mae, Masayuki
  • Imaizumi, Taiji

Abstract

In the context of escalating energy consumption in buildings, particularly from air conditioning (AC), the intelligent control of AC has become increasingly crucial. Accurately predicting future energy consumption for AC, the indoor environment, and determining the optimal settings have emerged as key challenges in intelligent AC control. In this study, a hybrid self-learning dynamic graph neural network with self-attention mechanism is proposed for AC forecasting. Addressing the gaps in the existing graph neural network applications, this model overcomes the limitations of static graph structures by constructing evolving adjacency matrices integrated with a gated recurrent unit and self-attention, effectively capturing the dynamic relationships between changing feature quantities. Additionally, a multi-task prediction (MTP) module that utilizes both past and future data is proposed. The MTP enables the application of a single model to multiple prediction tasks, thereby obviating the need for separate model training for each task. An experiment in an actual outdoor environment was designed to verify the predictive performance of the proposed model. The results indicate that the proposed model achieves superior accuracy for all target variables across different tasks under various AC conditions, particularly for variables with strong non-linearity, which showed a maximum improvement of 24.94% in correlation coefficient (R2) compared to long-short term memory network. With the MTP, the single model applied to multiple prediction tasks exhibited only a minimal sacrifice in accuracy, resulting in a mere 0.64% decrease in average R2 of all target variables for the proposed model.

Suggested Citation

  • Hu, Zehuan & Gao, Yuan & Sun, Luning & Mae, Masayuki & Imaizumi, Taiji, 2024. "Self-learning dynamic graph neural network with self-attention based on historical data and future data for multi-task multivariate residential air conditioning forecasting," Applied Energy, Elsevier, vol. 364(C).
    • Handle: RePEc:eee:appene:v:364:y:2024:i:c:s0306261924005397
    DOI: 10.1016/j.apenergy.2024.123156
    as

    Download full text from publisher

    File URL: http://www.sciencedirect.com/science/article/pii/S0306261924005397
    Download Restriction: Full text for ScienceDirect subscribers only
    File URL: https://libkey.io/10.1016/j.apenergy.2024.123156?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. Guefano, Serge & Tamba, Jean Gaston & Azong, Tchitile Emmanuel Wilfried & Monkam, Louis, 2021. "Forecast of electricity consumption in the Cameroonian residential sector by Grey and vector autoregressive models," Energy, Elsevier, vol. 214(C).
    2. Kim, Tae-Young & Cho, Sung-Bae, 2019. "Predicting residential energy consumption using CNN-LSTM neural networks," Energy, Elsevier, vol. 182(C), pages 72-81.
    3. Wang, Zhijin & Liu, Xiufeng & Huang, Yaohui & Zhang, Peisong & Fu, Yonggang, 2023. "A multivariate time series graph neural network for district heat load forecasting," Energy, Elsevier, vol. 278(PA).
    4. Wang, Zhe & Hong, Tianzhen & Piette, Mary Ann, 2020. "Building thermal load prediction through shallow machine learning and deep learning," Applied Energy, Elsevier, vol. 263(C).
    5. Chen, Zhiwen & Deng, Qiao & Ren, Hao & Zhao, Zhengrun & Peng, Tao & Yang, Chunhua & Gui, Weihua, 2022. "A new energy consumption prediction method for chillers based on GraphSAGE by combining empirical knowledge and operating data," Applied Energy, Elsevier, vol. 310(C).
    6. Imani, Maryam, 2021. "Electrical load-temperature CNN for residential load forecasting," Energy, Elsevier, vol. 227(C).
    7. Wang, Huan & Chen, Wenying & Shi, Jingcheng, 2018. "Low carbon transition of global building sector under 2- and 1.5-degree targets," Applied Energy, Elsevier, vol. 222(C), pages 148-157.
    8. Hu, Yuqing & Cheng, Xiaoyuan & Wang, Suhang & Chen, Jianli & Zhao, Tianxiang & Dai, Enyan, 2022. "Times series forecasting for urban building energy consumption based on graph convolutional network," Applied Energy, Elsevier, vol. 307(C).
    9. Hu, Zehuan & Gao, Yuan & Ji, Siyu & Mae, Masayuki & Imaizumi, Taiji, 2024. "Improved multistep ahead photovoltaic power prediction model based on LSTM and self-attention with weather forecast data," Applied Energy, Elsevier, vol. 359(C).
    10. Zhong, Hai & Wang, Jiajun & Jia, Hongjie & Mu, Yunfei & Lv, Shilei, 2019. "Vector field-based support vector regression for building energy consumption prediction," Applied Energy, Elsevier, vol. 242(C), pages 403-414.
    11. Gao, Yuan & Miyata, Shohei & Akashi, Yasunori, 2022. "Interpretable deep learning models for hourly solar radiation prediction based on graph neural network and attention," Applied Energy, Elsevier, vol. 321(C).
    12. Amasyali, Kadir & El-Gohary, Nora M., 2018. "A review of data-driven building energy consumption prediction studies," Renewable and Sustainable Energy Reviews, Elsevier, vol. 81(P1), pages 1192-1205.
    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. Yue, Naihua & Caini, Mauro & Li, Lingling & Zhao, Yang & Li, Yu, 2023. "A comparison of six metamodeling techniques applied to multi building performance vectors prediction on gymnasiums under multiple climate conditions," Applied Energy, Elsevier, vol. 332(C).
    2. Gao, Lei & Liu, Tianyuan & Cao, Tao & Hwang, Yunho & Radermacher, Reinhard, 2021. "Comparing deep learning models for multi energy vectors prediction on multiple types of building," Applied Energy, Elsevier, vol. 301(C).
    3. Venkatraj, V. & Dixit, M.K., 2022. "Challenges in implementing data-driven approaches for building life cycle energy assessment: A review," Renewable and Sustainable Energy Reviews, Elsevier, vol. 160(C).
    4. Somu, Nivethitha & M R, Gauthama Raman & Ramamritham, Krithi, 2020. "A hybrid model for building energy consumption forecasting using long short term memory networks," Applied Energy, Elsevier, vol. 261(C).
    5. Jason Runge & Radu Zmeureanu, 2021. "A Review of Deep Learning Techniques for Forecasting Energy Use in Buildings," Energies, MDPI, vol. 14(3), pages 1-26, January.
    6. Zhang, Xu & Sun, Yongjun & Gao, Dian-ce & Zou, Wenke & Fu, Jianping & Ma, Xiaowen, 2022. "Similarity-based grouping method for evaluation and optimization of dataset structure in machine-learning based short-term building cooling load prediction without measurable occupancy information," Applied Energy, Elsevier, vol. 327(C).
    7. Huang, Yaohui & Zhao, Yuan & Wang, Zhijin & Liu, Xiufeng & Liu, Hanjing & Fu, Yonggang, 2023. "Explainable district heat load forecasting with active deep learning," Applied Energy, Elsevier, vol. 350(C).
    8. Ding, Zhikun & Chen, Weilin & Hu, Ting & Xu, Xiaoxiao, 2021. "Evolutionary double attention-based long short-term memory model for building energy prediction: Case study of a green building," Applied Energy, Elsevier, vol. 288(C).
    9. Fath U Min Ullah & Noman Khan & Tanveer Hussain & Mi Young Lee & Sung Wook Baik, 2021. "Diving Deep into Short-Term Electricity Load Forecasting: Comparative Analysis and a Novel Framework," Mathematics, MDPI, vol. 9(6), pages 1-22, March.
    10. Lei, Lei & Shao, Suola & Liang, Lixia, 2024. "An evolutionary deep learning model based on EWKM, random forest algorithm, SSA and BiLSTM for building energy consumption prediction," Energy, Elsevier, vol. 288(C).
    11. Fu, Chun & Miller, Clayton, 2022. "Using Google Trends as a proxy for occupant behavior to predict building energy consumption," Applied Energy, Elsevier, vol. 310(C).
    12. Langevin, J. & Reyna, J.L. & Ebrahimigharehbaghi, S. & Sandberg, N. & Fennell, P. & Nägeli, C. & Laverge, J. & Delghust, M. & Mata, É. & Van Hove, M. & Webster, J. & Federico, F. & Jakob, M. & Camaras, 2020. "Developing a common approach for classifying building stock energy models," Renewable and Sustainable Energy Reviews, Elsevier, vol. 133(C).
    13. Ijaz Ul Haq & Amin Ullah & Samee Ullah Khan & Noman Khan & Mi Young Lee & Seungmin Rho & Sung Wook Baik, 2021. "Sequential Learning-Based Energy Consumption Prediction Model for Residential and Commercial Sectors," Mathematics, MDPI, vol. 9(6), pages 1-17, March.
    14. Lu, Yakai & Tian, Zhe & Zhou, Ruoyu & Liu, Wenjing, 2021. "A general transfer learning-based framework for thermal load prediction in regional energy system," Energy, Elsevier, vol. 217(C).
    15. Luo, X.J. & Oyedele, Lukumon O. & Ajayi, Anuoluwapo O. & Akinade, Olugbenga O. & Owolabi, Hakeem A. & Ahmed, Ashraf, 2020. "Feature extraction and genetic algorithm enhanced adaptive deep neural network for energy consumption prediction in buildings," Renewable and Sustainable Energy Reviews, Elsevier, vol. 131(C).
    16. Fan, Cheng & Sun, Yongjun & Xiao, Fu & Ma, Jie & Lee, Dasheng & Wang, Jiayuan & Tseng, Yen Chieh, 2020. "Statistical investigations of transfer learning-based methodology for short-term building energy predictions," Applied Energy, Elsevier, vol. 262(C).
    17. Liang, Xinbin & Liu, Zhuoxuan & Wang, Jie & Jin, Xinqiao & Du, Zhimin, 2023. "Uncertainty quantification-based robust deep learning for building energy systems considering distribution shift problem," Applied Energy, Elsevier, vol. 337(C).
    18. Yuwen You & Zhonghua Wang & Zhihao Liu & Chunmei Guo & Bin Yang, 2024. "Load Prediction of Regional Heat Exchange Station Based on Fuzzy Clustering Based on Fourier Distance and Convolutional Neural Network–Bidirectional Long Short-Term Memory Network," Energies, MDPI, vol. 17(16), pages 1-19, August.
    19. Chung, Won Hee & Gu, Yeong Hyeon & Yoo, Seong Joon, 2022. "District heater load forecasting based on machine learning and parallel CNN-LSTM attention," Energy, Elsevier, vol. 246(C).
    20. Wang, Ran & Lu, Shilei & Feng, Wei, 2020. "A novel improved model for building energy consumption prediction based on model integration," Applied Energy, Elsevier, vol. 262(C).

    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:364:y:2024:i:c:s0306261924005397. 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.