skip to main content
10.1145/3697355.3697401acmotherconferencesArticle/Chapter ViewAbstractPublication PagesbdiotConference Proceedingsconference-collections
research-article

Robust Spatio-Temporal Graph Neural Network for Electricity Consumption Forecasting

Published: 12 December 2024 Publication History

Abstract

Precise electricity consumption forecasting is pivotal in the energy schedule of new electric power systems. It is also significant for improving robustness of smart power grid. Existing multivariate time series predictions have made effective achievements in modeling sequential tendency and periodicity, but they lack of considering time series noises due to data sensing or transferring. Therefore, we focus on a robust approach to capture intricate correlations of multivariate time series data for forecasting. Specifically, we exploit gated dilated causal convolution as projection layer to capture latent semantic information from a temporal perspective. Furthermore, we combine time series decomposition and adaptive normalization to learn latent representations of each time series. Finally, we devise spatio-temporal modeling for capturing heterogeneous correlations. Extensive experiments are implemented on real-scenario public datasets. The performances show the effectiveness of proposed approach for electricity consumption forecasting.

References

[1]
Shaojie Bai, J Zico Kolter, and Vladlen Koltun. 2018. An empirical evaluation of generic convolutional and recurrent networks for sequence modeling. arXiv preprint arXiv:https://arXiv.org/abs/1803.01271 (2018).
[2]
Razvan-Gabriel Cirstea, Chenjuan Guo, et al. 2022. Triformer: Triangular, Variable-Specific Attentions for Long Sequence Multivariate Time Series Forecasting. In Proceedings of IJCAI. 1994–2001.
[3]
Jinliang Deng, Xiusi Chen, Renhe Jiang, Xuan Song, and Ivor W Tsang. 2021. St-norm: Spatial and temporal normalization for multi-variate time series forecasting. In Proceedings of ACM SIGKDD. 269–278.
[4]
Xiaochong Dong, Yingyun Sun, et al. 2021. Spatio-temporal convolutional network based power forecasting of multiple wind farms. Journal of Modern Power Systems and Clean Energy 10, 2 (2021), 388–398.
[5]
Wenqi Fan, Yao Ma, et al. 2019. Graph neural networks for social recommendation. In WWW. 417–426.
[6]
En Fu, Yinong Zhang, Fan Yang, and Shuying Wang. 2022. Temporal self-attention-based Conv-LSTM network for multivariate time series prediction. Neurocomputing 501 (2022), 162–173.
[7]
Guolin Ke, Qi Meng, Thomas Finley, et al. 2017. Lightgbm: A highly efficient gradient boosting decision tree. Advances in neural information processing systems 30 (2017).
[8]
Guokun Lai, Wei-Cheng Chang, Yiming Yang, and Hanxiao Liu. 2018. Modeling long-and short-term temporal patterns with deep neural networks. In The International ACM SIGIR. 95–104.
[9]
Aaron van den Oord, Sander Dieleman, et al. 2016. Wavenet: A generative model for raw audio. arXiv preprint arXiv:https://arXiv.org/abs/1609.03499 (2016).
[10]
Carlos A Severiano et al. 2021. Evolving fuzzy time series for spatio-temporal forecasting in renewable energy systems. Renewable Energy 171 (2021), 764–783.
[11]
Jelena et al. Simeunović. 2021. Spatio-temporal graph neural networks for multi-site PV power forecasting. IEEE Transactions on Sustainable Energy 13, 2 (2021), 1210–1220.
[12]
Fuyong Sun, Ruipeng Gao, Weiwei Xing, et al. 2022. Deep Fusion for Travel Time Estimation Based on Road Network Topology. IEEE Intelligent Systems (2022).
[13]
Fuyong Sun, Weiwei Xing, Xiaofei Tian, et al. 2023. Dual-norm based dynamic graph diffusion network for temporal prediction. Information Processing & Management 60, 4 (2023), 103387.
[14]
AR Troncoso-García et al. 2023. A new approach based on association rules to add explainability to time series forecasting models. Information Fusion 94 (2023), 169–180.
[15]
Ashish Vaswani, Noam Shazeer, et al. 2017. Attention is all you need. Advances in neural information processing systems 30 (2017).
[16]
Qingsong Wen, Jingkun Gao, et al. 2019. RobustSTL: A robust seasonal-trend decomposition algorithm for long time series. In Proceedings of the AAAI, Vol. 33. 5409–5416.
[17]
Zonghan Wu, Shirui Pan, Guodong Long, et al. 2020. Connecting the dots: Multivariate time series forecasting with graph neural networks. In Proceedings of the ACM SIGKDD. 753–763.
[18]
Zonghan Wu, Shirui Pan, Guodong Long, Jing Jiang, and Chengqi Zhang. 2019. Graph wavenet for deep spatial-temporal graph modeling. In Proceedings of the 28th IJCAI. 1907–1913.
[19]
Peter T Yamak et al. 2019. A comparison between arima, lstm, and gru for time series forecasting. In Proceedings of international conference on algorithms, computing and artificial intelligence. 49–55.
[20]
Linxiao Yang, Qingsong Wen, Bo Yang, and Liang Sun. 2021. A robust and efficient multi-scale seasonal-trend decomposition. In IEEE International Conference on Acoustics, Speech and Signal Processing. 5085–5089.
[21]
G Peter Zhang. 2003. Time series forecasting using a hybrid ARIMA and neural network model. Neurocomputing 50 (2003), 159–175.
[22]
Haoyi Zhou, Shanghang Zhang, et al. 2021. Informer: Beyond efficient transformer for long sequence time-series forecasting. In Proceedings of the AAAI, Vol. 35. 11106–11115.
[23]
Tian Zhou, Ziqing Ma, Qingsong Wen, Xue Wang, Liang Sun, and Rong Jin. 2022. FEDformer: Frequency enhanced decomposed transformer for long-term series forecasting. arXiv preprint arXiv:https://arXiv.org/abs/2201.12740 (2022).
[24]
Zhaoyang Zhu, Weiqi Chen, et al. 2023. eForecaster: unifying electricity forecasting with robust, flexible, and explainable machine learning algorithms. In Proceedings of the AAAI, Vol. 37. 15630–15638.
[25]
Eric Zivot and Jiahui Wang. 2006. Vector autoregressive models for multivariate time series. Modeling financial time series with S-PLUS® (2006), 385–429.

Index Terms

  1. Robust Spatio-Temporal Graph Neural Network for Electricity Consumption Forecasting

    Recommendations

    Comments

    Information & Contributors

    Information

    Published In

    cover image ACM Other conferences
    BDIOT '24: Proceedings of the 2024 8th International Conference on Big Data and Internet of Things
    September 2024
    412 pages
    ISBN:9798400717529
    DOI:10.1145/3697355
    Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than the author(s) must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected].

    Publisher

    Association for Computing Machinery

    New York, NY, United States

    Publication History

    Published: 12 December 2024

    Check for updates

    Author Tags

    1. electricity consumption forecasting
    2. spatio-temporal modeling
    3. data mining
    4. smart grid

    Qualifiers

    • Research-article

    Conference

    BDIOT 2024

    Acceptance Rates

    Overall Acceptance Rate 75 of 136 submissions, 55%

    Contributors

    Other Metrics

    Bibliometrics & Citations

    Bibliometrics

    Article Metrics

    • 0
      Total Citations
    • 18
      Total Downloads
    • Downloads (Last 12 months)18
    • Downloads (Last 6 weeks)8
    Reflects downloads up to 19 Feb 2025

    Other Metrics

    Citations

    View Options

    Login options

    View options

    PDF

    View or Download as a PDF file.

    PDF

    eReader

    View online with eReader.

    eReader

    Full Text

    View this article in Full Text.

    Full Text

    Figures

    Tables

    Media

    Share

    Share

    Share this Publication link

    Share on social media