AI Chat Paper
Note: Please note that the following content is generated by AMiner AI. SciOpen does not take any responsibility related to this content.
{{lang === 'zh_CN' ? '文章概述' : 'Summary'}}
{{lang === 'en_US' ? '中' : 'Eng'}}
Chat more with AI
Powered by AMiner. Clicking this button will take you away from SciOpen.
Home Tsinghua Science and Technology Article
PDF (2.1 MB)
Cite
EndNote(RIS) BibTeX
Collect
Submit Manuscript AI Chat Paper
Show Outline
Outline
Show full outline
Hide outline
Outline
Show full outline
Hide outline
Open Access

STDNet: A Spatio-Temporal Decomposition Neural Network for Multivariate Time Series Forecasting

College of Computer Science and Technology (College of Data Science), Taiyuan University of Technology, Jinzhong 030600, China
Show Author Information

Abstract

Long-term multivariate time series forecasting is an important task in engineering applications. It helps grasp the future development trend of data in real-time, which is of great significance for a wide variety of fields. Due to the non-linear and unstable characteristics of multivariate time series, the existing methods encounter difficulties in analyzing complex high-dimensional data and capturing latent relationships between multivariates in time series, thus affecting the performance of long-term prediction. In this paper, we propose a novel time series forecasting model based on multilayer perceptron that combines spatio-temporal decomposition and doubly residual stacking, namely Spatio-Temporal Decomposition Neural Network (STDNet). We decompose the originally complex and unstable time series into two parts, temporal term and spatial term. We design temporal module based on auto-correlation mechanism to discover temporal dependencies at the sub-series level, and spatial module based on convolutional neural network and self-attention mechanism to integrate multivariate information from two dimensions, global and local, respectively. Then we integrate the results obtained from the different modules to get the final forecast. Extensive experiments on four real-world datasets show that STDNet significantly outperforms other state-of-the-art methods, which provides an effective solution for long-term time series forecasting.

Keywords

time series forecastingmultivariate time seriesspatio-temporal decomposition

References

[1]
V. L. Guen and N. Thome, Shape and time distortion loss for training deep time series forecasting models, arXiv preprint arXiv: 1909.09020, 2019.
[2]
Y. Zhu and D. Shasha, Statstream: Statistical monitoring of thousands of data streams in real time, in Proc. 28th Int. Conf. Very Large Data Bases, Hong Kong, China, 2002, pp. 358–369.
Crossref
[3]

C. Deb, F. Zhang, J. Yang, S. E. Lee, and K. W. Shah, A review on time series forecasting techniques for building energy consumption, Renew. Sustain. Energy Rev., vol. 74, pp. 902–924, 2017.
Crossref Google Scholar
[4]

F. Kong, J. Li, B. Jiang, and H. Song, Short-term traffic flow prediction in smart multimedia system for Internet of Vehicles based on deep belief network, Future Gener. Comput. Syst., vol. 93, pp. 460–472, 2019.
Crossref Google Scholar
[5]

N. Guo, W. Chen, M. L. Wang, Z. J. Tian, and H. Y. Jin, Appling an improved method based on ARIMA model to predict the short-term electricity consumption transmitted by the Internet of Things (IoT), Wirel. Commun. Mob. Comput., vol. 2021, pp. 1–11, 2021.
Crossref Google Scholar
[6]

Z. Y. Zhu, L. Liu, and M. Cui, Short-term traffic flow forecasting model combining SVM and Kalman filtering, (in Chinese), Comput. Sci., vol. 40, no. 10, pp. 248–251, 2013.
Google Scholar
[7]
X. B. Jin, X. H. Yu, X. Y. Wang, Y. T. Bai, T. L. Su, and J. L. Kong, Prediction for time series with CNN and LSTM, in Proc. 11th Int. Conf. Modelling, Identification and Control (ICMIC2019), Tianjin, China, 2020, pp. 631–641.
Crossref
[8]

S. Y. Shih, F. K. Sun, and H. Y. Lee, Temporal pattern attention for multivariate time series forecasting, Mach. Learn., vol. 108, no. 8, pp. 1421–1441, 2019.
Crossref Google Scholar
[9]
Z. Wu, S. Pan, G. Long, J. Jiang, X. Chang, and C. Zhang, Connecting the dots: Multivariate time series forecasting with graph neural networks, in Proc. 26th ACM SIGKDD Int. Conf. Knowledge Discovery & Data Mining, Virtual Event, 2020, pp. 753–763.
Crossref
[10]
H. Miao, Y. Zhang, Z. Ning, Z. Jiang, and L. Wang, TDG4MSF: A temporal decomposition enhanced graph neural network for multivariate time series forecasting, Appl. Intell.
[11]
B. N. Oreshkin, D. Carpo, N. Chapados, and Y. Bengio, N-BEATS: Neural basis expansion analysis for interpretable time series forecasting, arXiv preprint arXiv: 1905.10437, 2019.
[12]

P. Esling and C. Agon, Time-series data mining, ACM Comput. Surv., vol. 45, no. 1, p. 12, 2012.
Crossref Google Scholar
[13]

V. Mnih, N. Heess, A. Graves, and K. Kavukcuoglu, Recurrent models of visual attention, in Proc. 27th Int. Conf. Neural Information Processing Systems, Montreal, Canada, 2014, pp. 2204–2212.
Google Scholar
[14]

H. Abbasimehr and R. Paki, Improving time series forecasting using LSTM and attention models, J. Ambient Intell. Humaniz. Comput., vol. 13, no. 1, pp. 673–691, 2022.
Crossref Google Scholar
[15]

J. Fan, K. Zhang, Y. Huang, Y. Zhu, and B. Chen, Parallel spatio-temporal attention-based TCN for multivariate time series prediction, Neural Comput. Appl., vol. 35, no. 18, pp. 13109–13118, 2023.
Crossref Google Scholar
[16]
A. Vaswani, N. Shazeer, N. Parmar, J. Uszkoreit, L. Jones, A. N. Gomez, L. Kaiser, and I. Polosukhin, Attention is all you need, arXiv preprint arXiv: 1706.03762, 2017.
[17]
S. Li, X. Jin, Y. Xuan, X. Zhou, W. Chen, Y. X. Wang, and X. Yan, Enhancing the locality and breaking the memory bottleneck of transformer on time series forecasting, arXiv preprint arXiv: 1907.00235, 2019.
[18]

H. Zhou, S. Zhang, J. Peng, S. Zhang, J. Li, H. Xiong, and W. Zhang, Informer: Beyond efficient transformer for long sequence time-series forecasting, Proc. AAAI Conf. Artif. Intell., vol. 35, no. 12, pp. 11106–11115, 2021.
Crossref Google Scholar
[19]
H. Wu, J. Xu, J. Wang, and M. Long, Autoformer: Decomposition transformers with auto-correlation for long-term series forecasting, arXiv preprint arXiv: 2106.13008, 2021.
[20]

K. G. Olivares, C. Challu, G. Marcjasz, R. Weron, and A. Dubrawski, Neural basis expansion analysis with exogenous variables: Forecasting electricity prices with NBEATSx, Int. J. Forecast., vol. 39, no. 2, pp. 884–900, 2023.
Crossref Google Scholar
[21]

H. Wen, J. Gu, J. Ma, L. Yuan, and Z. Jin, Probabilistic load forecasting via neural basis expansion model based prediction intervals, IEEE Trans. Smart Grid, vol. 12, no. 4, pp. 3648–3660, 2021.
Crossref Google Scholar
[22]

B. N. Oreshkin, D. Carpov, N. Chapados, and Y. Bengio, Meta-learning framework with applications to zero-shot time-series forecasting, Proc. AAAI Conf. Artif. Intell., vol. 35, no. 10, pp. 9242–9250, 2021.
Crossref Google Scholar
[23]
X. Chen and L. Sun, Low-rank autoregressive tensor completion for multivariate time series forecasting, arXiv preprint arXiv: 2006.10436, 2020.
[24]

B. N. Oreshkin, A. Amini, L. Coyle, and M. Coates, FC-GAGA: Fully connected gated graph architecture for spatio-temporal traffic forecasting, Proc. AAAI Conf. Artif. Intell., vol. 35, no. 10, pp. 9233–9241, 2021.
Crossref Google Scholar
[25]
Z. Ning, Z. Jiang, H. Miao, and L. Wang, MST-GNN: A multi-scale temporal-enhanced graph neural network for anomaly detection in multivariate time series, in Web and Big Data, B. Li, L. Yue, C. Tao, X. Han, D. Calvanese, and T. Amagasa, eds. Cham, Switzerland: Springer, 2023, pp. 382–390.
Crossref
[26]
A. Tran, A. Mathews, C. S. Ong, and L. Xie, Radflow: A recurrent, aggregated, and decomposable model for networks of time series, in Proc. Web Conf. 2021, Ljubljana, Slovenia, 2021, pp. 730–742.
Crossref
[27]
S. Bai, J. Z. Kolter, and V. Koltun, An empirical evaluation of generic convolutional and recurrent networks for sequence modeling, arXiv preprint arXiv: 1803.01271, 2018.
[28]

S. Hochreiter and J. Schmidhuber, Long short-term memory, Neural Comput., vol. 9, no. 8, pp. 1735–1780, 1997.
Crossref Google Scholar
[29]
G. Lai, W. C. Chang, Y. Yang, and H. Liu, Modeling long- and short-term temporal patterns with deep neural networks, in Proc. SIGIR '18 : The 41st Int. ACM SIGIR Conf. Research & Development in Information Retrieval, Ann Arbor, MI, USA, 2018, pp. 95–104.
Crossref
[30]
N. Kitaev, L. Kaiser, and A. Levskaya, Reformer: The efficient transformer, presented at the Int. Conf. Learning Representations (ICLR), New Orleans, LA, USA, 2019.
[31]

C. Challu, K. G. Olivares, B. N. Oreshkin, F. G. Ramirez, M. M. Canseco, and A. Dubrawski, NHITS: Neural hierarchical interpolation for time series forecasting, Proc. AAAI Conf. Artif. Intell., vol. 37, no. 6, pp. 6989–6997, 2023.
Crossref Google Scholar
[32]
W. Xu, W. Liu, J. Bian, J. Yin, and T. Y. Liu, Instance-wise graph-based framework for multivariate time series forecasting, arXiv preprint arXiv: 2109.06489, 2021.
Tsinghua Science and Technology
Volume 29 Issue 4,
August 2024
Pages 1232-1247
DOI: 10.26599/TST.2023.9010105
Cite this article:
Jiang Z, Ning Z, Miao H, et al. STDNet: A Spatio-Temporal Decomposition Neural Network for Multivariate Time Series Forecasting. Tsinghua Science and Technology, 2024, 29(4): 1232-1247. https://doi.org/10.26599/TST.2023.9010105

423

Views

52

Downloads

1

Crossref

1

Web of Science

2

Scopus

0

CSCD

Altmetrics
Received: 01 July 2023
Revised: 14 September 2023
Accepted: 26 September 2023
Published: 09 February 2024
© The Author(s) 2024.

The articles published in this open access journal are distributed under the terms of theCreative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/).
Return