时空图神经网络在物联网中的应用综述

doi:10.3778/j.issn.1002-8331.2404-0043

摘要/Abstract

摘要： 随着物联网在各个领域物理设备的发展，产生的大量数据给当前数据处理方法带来了挑战。深度学习模型具备处理大规模和高维度数据的能力，已逐渐应用于物联网不同领域。时空图神经网络作为一种处理图结构数据的深度学习模型，能够对物联网中的拓扑结构和时间信息进行建模，并在物联网预测任务中展现出优秀性能。介绍了物联网中的时间相关性和空间相关性，以及不同时空网络架构的构建方法，并基于空间相关性的不同，将时空图神经网络分为时空图卷积网络和时空图注意力网络。进一步分析了时空图卷积网络和时空图注意力网络在物联网中的应用，主要包括交通、环境和能源领域。最后，探讨了时空图神经网络在物联网应用中面临的挑战和未来的研究方向。

关键词: 物联网, 深度学习, 时空图神经网络, 图结构数据

Abstract: With the development of physical devices in various fields of the Internet of things(IoT), the large amount of data generated has brought challenges to current data processing methods. Deep learning models have the ability to process large-scale and high-dimensional data, and have gradually been applied to different fields of the Internet of things. As a deep learning model for processing graph structured data, spatiotemporal graph neural network can model the topological structure and temporal information in the Internet of things and show excellent performance in the prediction tasks of the Internet of things. Firstly, the temporal correlation and spatial correlation in the Internet of things, as well as the construction methods of different spatiotemporal network architectures are introduced. Based on the difference in spatial correlation, the spatiotemporal graph neural network is divided into spatiotemporal graph convolutional network and spatiotemporal graph attention network. Then, the application of spatiotemporal graph convolutional network and spatiotemporal graph attention network in the Internet of things is further analyzed, mainly including the fields of transportation, environment and energy. Finally, the challenges faced by spatiotemporal graph neural network in the application of the Internet of things and the future research directions are discussed.

Key words: Internet of things(IoT), deep learning, spatiotemporal graph neural network, graph-structured data

张建伟, 陈旭, 王叔洋, 景永俊, 宋吉飞. 时空图神经网络在物联网中的应用综述[J]. 计算机工程与应用, 2025, 61(5): 43-54.

ZHANG Jianwei, CHEN Xu, WANG Shuyang, JING Yongjun, SONG Jifei. Review of Application of Spatiotemporal Graph Neural Networks in Internet of Things[J]. Computer Engineering and Applications, 2025, 61(5): 43-54.

参考文献

[1] LI H, ZHAO Y, MAO Z, et al. A survey on graph neural networks in intelligent transportation systems[J]. arXiv:2401.00713,2024.
[2] BARTHWAL A. A Markov chain-based IoT system for monitoring and analysis of urban air quality[J]. Environmental Monitoring and Assessment, 2022, 195(1): 235.
[3] NAUCK C, LINDNER M, SCHüRHOLT K, et al. Toward dynamic stability assessment of power grid topologies using graph neural networks[J]. arXiv:2206.06369, 2022.
[4] 李莉, 时榕良, 郭旭, 等. 融合大模型与图神经网络的电力设备缺陷诊断[J]. 计算机科学与探索, 2024, 18(10): 2643-2655.
LI L, SHI R L, GUO X, et al. Diagnosis of power system defects by large language models and graph neural networks[J]. Journal of Frontiers of Computer Science and Technology, 2024, 18(10): 2643-2655.
[5] WAIKHOM L, PATGIRI R. A survey of graph neural networks in various learning paradigms: methods, applications, and challenges[J]. Artificial Intelligence Review, 2023, 56(7): 6295-6364.
[6] CHO K, MERRIENBOER V B, BAHDANAU D, et al. On the properties of neural machine translation: encoder-decoder approaches[C]//Proceedings of the 8th Workshop on Syntax, Semantics and Structure in Statistical Translation, 2014: 103-111.
[7] KIPF T N, WELLING M. Semi-supervised classification with graph convolutional networks[J]. arXiv:1609.02907, 2016.
[8] ZHANG S Y, ZHANG H, CUI S G, et al. From spectrum wavelet to vertex propagation: graph convolutional networks based on Taylor approximation[J]. arXiv:2007.00730, 2020.
[9] DANEL T, SPUREK P, TABOR J, et al. Spatial graph convolutional networks[J]. arXiv:1909.05310, 2019.
[10] VASWANI A, SHAZEER N, PARMAR N, et al. Attention is all you need[C]//Proceedings of the 31st International Conference on Neural Information Processing Systems, 2017: 6000-6010.
[11] VELI?KOVI? P, CUCURULL G, CASANOVA A, et al. Graph attention networks[J]. arXiv: 1710. 10903, 2017.
[12] 李朝阳, 李琳, 陶晓辉. 面向动态交通流预测的双流图卷积网络[J]. 计算机科学与探索, 2022, 16(2): 384-394.
LI Z Y, LI L, TAO X H. Two-stream graph convolutional neural network for dynamic traffic flow forecasting[J]. Journal of Frontiers of Computer Science and Technology, 2022, 16(2): 384-394.
[13] 李金中, 王小明, 谢毓广, 等. 融合时空特征的光伏气象因子预测模型[J]. 计算机工程与应用, 2022, 58(23): 285-292.
LI J Z, WANG X M, XIE Y G, et al. Photovoltaic meteorological factor prediction model fusing spatial and temporal features[J]. Computer Engineering and Applications, 2022, 58(23): 285-292.
[14] REN X Y, YUAN S X. GCN-LSTM combined model for urban link mean speed prediction in the regional traffic network[C]//Proceedings of the 2022 IEEE International Conference on Dependable, Autonomic and Secure Computing, International Conference on Pervasive Intelligence and Computing, International Conference on Cloud and Big Data Computing, International Conference on Cyber Science and Technology Congress, 2022: 1-7.
[15] KUMAR R, MOREIRA M J, CHANDRA J. DyGCN-LSTM: a dynamic GCN-LSTM based encoder-decoder framework for multistep traffic prediction[J]. Applied Inte-
lligence, 2023, 53(21): 25388-25411.
[16] LUO Y, ZHENG J Y, WANG X, et al. GT-LSTM: a spatio-temporal ensemble network for traffic flow prediction[J]. Neural Networks, 2024, 171: 251-262.
[17] QI Y L, LI Q, KARIMIAN H, et al. A hybrid model for spatiotemporal forecasting of PM2. 5 based on graph convolutional neural network and long short-term memory[J]. Science of the Total Environment, 2019, 664: 1-10.
[18] SONG Y Y, MAO H Y, LI H W. Spatio-temporal modeling for air quality prediction based on spectral graph convolutional network and attention mechanism[C]//Proceedings of the 2022 International Joint Conference on Neural Networks, 2022: 1-9.
[19] LIAO W L, BAK-JENSEN B, PILLAI J R, et al. Short-term power prediction for renewable energy using hybrid graph convolutional network and long short-term memory approach[J]. Electric Power Systems Research, 2022, 211: 108614.
[20] SIMEUNOVI? J, SCHUBNEL B, ALET P J, et al. Spatio-temporal graph neural networks for multi-site PV power forecasting[J]. IEEE Transactions on Sustainable Energy, 2022, 13(2): 1210-1220.
[21] KHODAYAR M, WANG J H. Spatio-temporal graph deep neural network for short-term wind speed forecasting[J]. IEEE Transactions on Sustainable Energy, 2019, 10(2): 670-681.
[22] ZHAO L, SONG Y J, ZHANG C, et al. T-GCN: a temporal graph convolutional network for traffic prediction[J]. IEEE Transactions on Intelligent Transportation Systems, 2020, 21(9): 3848-3858.
[23] ZHU J, SONG Y, ZHAO L, et al. A3T-GCN: attention temporal graph convolutional network for traffic forecasting[J]. ISPRS International Journal of Geo-Information, 2021, 10(7): 485.
[24] YANG J, LI J H, WEI L, et al. ST-AGRNN: a spatio-temporal attention-gated recurrent neural network for traffic state forecasting[J]. Journal of Advanced Transportation, 2022, 2022(1): 2806183.
[25] ZHENG Y, WANG S Y, DONG C J, et al. Urban road traffic flow prediction: a graph convolutional network embedded with wavelet decomposition and attention mechanism[J]. Physica A: Statistical Mechanics and Its Applications, 2022, 608: 128274.
[26] XIAO X, JIN Z L, WANG S, et al. A dual-path dynamic directed graph convolutional network for air quality prediction[J]. Science of the Total Environment, 2022, 827: 154298.
[27] OUYANG X C, YANG Y, ZHANG Y L, et al. Spatial-temporal dynamic graph convolution neural network for air quality prediction[C]//Proceedings of the 2021 International Joint Conference on Neural Networks, 2021: 1-8.
[28] HU Y, LI Q, SHI X, et al. Multi-spatial multi-temporal air quality forecasting with integrated monitoring and reanalysis data[J]. arXiv:2401.00521, 2024.
[29] CHEN Z, ZHANG B, DU C, et al. A novel dynamic spatio-temporal graph convolutional network for wind speed interval prediction[J]. Energy, 2024, 294: 130930.
[30] XU X F, HU S T, SHAO H S, et al. A spatio-temporal forecasting model using optimally weighted graph convolutional network and gated recurrent unit for wind speed of different sites distributed in an offshore wind farm[J]. Energy, 2023, 284: 128565.
[31] YU B, YIN H T, ZHU Z X, et al. Spatio-temporal graph convolutional networks[C]//Proceedings of the 27th International Joint Conference on Artificial Intelligence, 2018: 3634-3640.
[32] DIAO Z L, WANG X, ZHANG D F, et al. Dynamic spatial-temporal graph convolutional neural networks for traffic forecasting[C]//Proceedings of the 33rd AAAI Conference on Artificial Intelligence and 31st Innovative Applications of Artificial Intelligence Conference and 9th AAAI Symposium on Educational Advances in Artificial Intelligence, 2019: 890-897.
[33] TANG C, SUN J R, SUN Y C. Dynamic spatial-temporal graph attention graph convolutional network for short-term traffic flow forecasting[C]//Proceedings of the 2020 IEEE International Symposium on Circuits and Systems, 2020: 1-5.
[34] ZHOU H Y, ZHANG F, DU Z H, et al. Forecasting PM2.5 using hybrid graph convolution-based model considering dynamic wind-field to offer the benefit of spatial interpretability[J]. Environmental Pollution, 2021, 273: 116473.
[35] ZENG Q T, WANG C, CHEN G, et al. PM2.5 concentration forecasting in industrial parks based on attention mechanism spatiotemporal graph convolutional networks[J]. Wireless Communications and Mobile Computing, 2021(1): 7000986.
[36] KARIMI A M, WU Y H, KOYUTURK M, et al. Spatiotemporal graph neural network for performance prediction of photovoltaic power systems[C]//Proceedings of the AAAI Conference on Artificial Intelligence, 2021: 15323-15330.
[37] SONG Y, TANG D Y, YU J S, et al. Short-term forecasting based on graph convolution networks and multiresolution convolution neural networks for wind power[J]. IEEE Transactions on Industrial Informatics, 2023, 19(2): 1691-1702.
[38] ZHANG C H, YU J J Q, LIU Y. Spatial-temporal graph attention networks: a deep learning approach for traffic forecasting[J]. IEEE Access, 2019, 7: 166246-166256.
[39] FANG Y J, JIANG J, HE Y X. Traffic speed prediction based on LSTM-graph attention network (L-GAT)[C]//Proceedings of the 2021 4th International Conference on Advanced Electronic Materials, Computers and Software Engineering, 2021: 788-793.
[40] AYKAS D, MEHRKANOON S. Multistream graph attention networks for wind speed forecasting[C]//Proceedings of the 2021 IEEE Symposium Series on Computational Intelligence, 2021: 1-8.
[41] ZHANG K J, ZHANG X, SONG H T, et al. Air quality prediction model based on spatiotemporal data analysis and metalearning[J]. Wireless Communications and Mobile Computing, 2021, 2021(1): 9627776.
[42] LIU T, GU X P, LI S Y, et al. Static voltage stability margin prediction considering new energy uncertainty based on graph attention networks and long short-term memory networks[J]. IET Renewable Power Generation, 2023, 17(9): 2290-2301.
[43] HE H Y, FU F Y, LUO D S. Multiplex parallel GAT-ALSTM: a novel spatial-temporal learning model for multi-sites wind power collaborative forecasting[J]. Frontiers in Energy Research, 2022, 10: 974682.
[44] ZHANG J, SHI X, XIE J, et al. GaAN: gated attention networks for learning on large and spatiotemporal graphs[J]. arXiv:1803.07294, 2018.
[45] ZHAO Y P, XU Y P, HE X T, et al. Spatiotemporal graph attention networks for urban traffic flow prediction[C]//Proceedings of the 2022 IEEE 33rd Annual International Symposium on Personal, Indoor and Mobile Radio Communications, 2022: 340-345.
[46] YU X, SHI S X, XU L Y. A spatial-temporal graph attention network approach for air temperature forecasting[J]. Applied Soft Computing, 2021, 113: 107888.
[47] WANG S, QIAO L, FANG W, et al. Air pollution prediction via graph attention network and gated recurrent unit[J]. Computers, Materials & Continua, 2022, 73(1): 673-687.
[48] WANG L, HE Y G. M2STAN: multi-modal multi-task spatio temporal attention network for multi-location ultra-short-term wind power multi-step predictions[J]. Applied Energy, 2022, 324: 119672.
[49] YU C Q, YAN G X, YU C M, et al. A multi-factor driven spatiotemporal wind power prediction model based on ensemble deep graph attention reinforcement learning networks[J]. Energy, 2023, 263: 126034.
[50] KONG X Y, XING W W, WEI X, et al. STGAT: spatial-temporal graph attention networks for traffic flow forecasting[J]. IEEE Access, 2020, 8: 134363-134372.
[51] KONG X Y, ZHANG J, WEI X, et al. Adaptive spatial-temporal graph attention networks for traffic flow forecasting[J]. Applied Intelligence, 2022, 52(4): 4300-4316.
[52] ZHAO P J, ZETTSU K. MASTGN: multi-attention spatio-temporal graph networks for air pollution prediction[C]//Proceedings of the 2020 IEEE International Conference on Big Data, 2020: 1442-1448.
[53] ZHENG C P, FAN X L, WANG C, et al. GMAN: a graph multi-attention network for traffic prediction[C]//Proceedings of the AAAI Conference on Artificial Intelligence, 2020: 1234-1241.
[54] JIN Z L, XU J, HUANG R Q, et al. STM2CN: a multi-graph attention-based framework for sensor data prediction in smart cities[C]//Proceedings of the 2022 International Joint Conference on Neural Networks, 2022: 1-8.
[55] SHAO W, JIN Z L, WANG S, et al. Long-term spatio-temporal forecasting via dynamic multiple-graph attention[C]//Proceedings of the 31st International Joint Conference on Artificial Intelligence, 2022: 2225-2232.
[56] LO W W, LAYEGHY S, SARHAN M, et al.E-GraphSAGE: a graph neural network based intrusion detection system for IoT[C]//Proceedings of the 2022 IEEE/IFIP Network Operations and Management Symposium, 2022: 1-9.
[57] DENG P, ZHAO Y, LIU J T, et al. Spatio-temporal neural structural causal models for bike flow prediction[C]//Proceedings of the AAAI Conference on Artificial Intelligence, 2023: 4242-4249.