[1]孟祥福,谢伟鹏,崔江燕.基于时空动态图的交通流量预测方法研究[J].智能系统学报,2025,20(4):776-786.[doi:10.11992/tis.202402012]
MENG Xiangfu,XIE Weipeng,CUI Jiangyan.Research on traffic flow prediction method based on spatial-temporal dynamic graph convolutional network[J].CAAI Transactions on Intelligent Systems,2025,20(4):776-786.[doi:10.11992/tis.202402012]
点击复制
MENG Xiangfu,XIE Weipeng,CUI Jiangyan.Research on traffic flow prediction method based on spatial-temporal dynamic graph convolutional network[J].CAAI Transactions on Intelligent Systems,2025,20(4):776-786.[doi:10.11992/tis.202402012]
基于时空动态图的交通流量预测方法研究
《智能系统学报》[ISSN 1673-4785/CN 23-1538/TP] 卷:
20
期数:
2025年第4期
页码:
776-786
栏目:
学术论文—机器学习
出版日期:
2025-08-05
- Title:
- Research on traffic flow prediction method based on spatial-temporal dynamic graph convolutional network
- Keywords:
- traffic flow; spatio-temporal data; hybrid model; attention mechanism; spatio-temporal dynamic graph; graph convolutional neural network; recurrent neural network; deep learning
- 分类号:
- TP302.7
- 文献标志码:
- 2025-2-25
- 摘要:
- 为改进现有交通流量预测方法在建模时空数据和捕捉动态空间相关性方面的不足，提出了一种时空动态图卷积网络（spatio-temporal dynamic graph network，STDGNet）。该模型采用带嵌入层的编码器–解码器架构，通过动态图生成模块从数据驱动的角度挖掘潜在的时空关系，并重构每个时间步的节点动态关联图。嵌入层使用时空自适应嵌入方法建模交通数据的内在时空关系和时间信息；编码器部分利用时空记忆注意力机制，从全局视角对时空特征进行建模；解码器部分将图卷积模块注入循环神经网络中，以同时捕捉时间和空间依赖关系，并输出未来流量情况。实验结果表明，所提模型与最优基线模型解耦动态时空图神经网络（decoupled dynamic spatial-temporal graph neural network，D2STGNN）相比，平均绝对误差降低了1.63%，模型训练时间缩短了近2.5倍。本研究有效提升了交通流量预测的准确性与效率，为智能交通系统的建设提供了有力支撑。
- Abstract:
- To address the limitations of existing traffic flow prediction methods in modeling spatio-temporal data and capturing dynamic spatial correlations, a spatio-temporal dynamic graph network(STDGNet) is proposed. This model adopts an encoder-decoder architecture with an embedding layer and utilizes a dynamic graph generation module to uncover potential spatio-temporal relationships from a data-driven perspective, reconstructing the dynamic correlation graph of nodes at each time step. The embedding layer employs a spatio-temporal adaptive embedding method to model the intrinsic spatio-temporal relationships and temporal information of traffic data. The encoder part uses a spatio-temporal memory attention mechanism to model spatio-temporal features from a global perspective. The decoder part incorporates a graph convolution module into a recurrent neural network to simultaneously capture temporal and spatial dependencies and output future traffic conditions. Experimental results show that, compared with the optimal baseline model decoupled dynamic spatial-temporal graph neural network(D2STGNN), the proposed model reduces mean absolute error by an average of 1.63% and reduces model training time by nearly 2.5 times. This study effectively improves the accuracy and efficiency of traffic flow prediction, providing strong support for the development of intelligent transportation systems.
- 参考文献/References:
-
[1] YIN Chuantao, XIONG Zhang, CHEN Hui, et al. A literature survey on smart cities[J]. Science China information sciences, 2015, 58(10): 1-18.
[2] BARNES R, BUTHPITIYA S, COOK J, et al. BusTr: predicting bus travel times from real-time traffic[C]//Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining. Virtual Event: ACM, 2020: 3243-3251.
[3] JIANG Renhe, YIN Du, WANG Zhaonan, et al. DL-traff: survey and benchmark of deep learning models for urban traffic prediction[C]//Proceedings of the 30th ACM International Conference on Information & Knowledge Management. New York: ACM, 2021: 4515–4525.
[4] WANG Jingyuan, JIANG Jiawei, JIANG Wenjun, et al. LibCity: an open library for traffic prediction[C]//Proceedings of the 29th International Conference on Advances in Geographic Information Systems. New York: ACM, 2021: 145–148.
[5] FU Quanlu, WU Jiyan, WU Xuemian, et al. Managing network congestion with link-based incentives: a surrogate-based optimization approach[J]. Transportation research part A: policy and practice, 2024, 182: 104033.
[6] SATTARZADEH A R, KUTADINATA R J, PATHIRANA P N, et al. A novel hybrid deep learning model with ARIMA Conv-LSTM networks and shuffle attention layer for short-term traffic flow prediction[J]. Transportmetrica A: transport science, 2025, 21(1): 2236724.
[7] XU Xuecai, JIN Xiaofei, XIAO Daiquan, et al. A hybrid autoregressive fractionally integrated moving average and nonlinear autoregressive neural network model for short-term traffic flow prediction[J]. Journal of intelligent transportation systems, 2023, 27(1): 1-18.
[8] KHAN A, FOUDA M M, DO D T, et al. Short-term traffic prediction using deep learning long short-term memory: taxonomy, applications, challenges, and future trends[J]. IEEE access, 2023, 11: 94371-94391.
[9] DAI Genan, KONG Weiyang, LIU Yubao, et al. Multi-perspective convolutional neural networks for citywide crowd flow prediction[J]. Applied intelligence, 2023, 53(8): 8994-9008.
[10] ZHANG Si, TONG Hanghang, XU Jiejun, et al. Graph convolutional networks: a comprehensive review[J]. Computational social networks, 2019, 6(1): 11.
[11] WU Zonghan, PAN Shirui, CHEN Fengwen, et al. A comprehensive survey on graph neural networks[J]. IEEE transactions on neural networks and learning systems, 2021, 32(1): 4-24.
[12] GUO Shengnan, LIN Youfang, FENG Ning, et al. Attention based spatial-temporal graph convolutional networks for traffic flow forecasting[C]//Proceedings of the AAAI Conference on Artificial Intelligence. Palo Alto: AAAI, 2019, 33(1): 922-929.
[13] JIANG Renhe, WANG Zhaonan, YONG Jiawei, et al. Spatio-temporal meta-graph learning for traffic forecasting[C]//Proceedings of the AAAI Conference on Artificial Intelligence. Palo Alto: AAAI, 2023: 8078-8086.
[14] SHIN Y, YOON Y. PGCN: progressive graph convolutional networks for spatial-temporal traffic forecasting[J]. IEEE transactions on intelligent transportation systems, 2024, 25(7): 7633-7644.
[15] ZHENG Chuanpan, FAN Xiaoliang, WANG Cheng, et al. Gman: a graph multi-attention network for traffic prediction[C]//Proceedings of the AAAI Conference on Artificial Intelligence. Palo Alto: AAAI, 2020: 1234-1241.
[16] LIPPI M, BERTINI M, FRASCONI P. Short-term traffic flow forecasting: an experimental comparison of time-series analysis and supervised learning[J]. IEEE transactions on intelligent transportation systems, 2013, 14(2): 871-882.
[17] WANG Jian, DENG Wei, GUO Yuntao. New Bayesian combination method for short-term traffic flow forecasting[J]. Transportation research part C: emerging technologies, 2014, 43: 79-94.
[18] SHAHRIARI S, GHASRI M, SISSON S A, et al. Ensemble of ARIMA: combining parametric and bootstrapping technique for traffic flow prediction[J]. Transportmetrica A: transport science, 2020, 16(3): 1552-1573.
[19] WILLIAMS B M, HOEL L A. Modeling and forecasting vehicular traffic flow as a seasonal ARIMA process: theoretical basis and empirical results[J]. Journal of transportation engineering, 2003, 129(6): 664-672.
[20] RAZA A, LIU Guangjie, ADEKE J M, et al. Passenger flow prediction method based on hybrid algorithm: intelligent transportation system[J]. European journal of applied science, engineering and technology, 2024, 2(1): 12-20.
[21] LUO Xianglong, LI Danyang, ZHANG Shengrui. Traffic flow prediction during the holidays based on DFT and SVR[J]. Journal of sensors, 2019, 2019: 6461450.
[22] YANG Xiaoxue, ZOU Yajie, TANG Jinjun, et al. Evaluation of short-term freeway speed prediction based on periodic analysis using statistical models and machine learning models[J]. Journal of advanced transportation, 2020, 2020: 9628957.
[23] XIA Dawen, WANG Binfeng, LI Huaqing, et al. A distributed spatial-temporal weighted model on MapReduce for short-term traffic flow forecasting[J]. Neurocomputing, 2016, 179: 246-263.
[24] SUN Zhaoyun, HU Yuanjiao, LI Wei, et al. Prediction model for short-term traffic flow based on a K-means-gated recurrent unit combination[J]. IET intelligent transport systems, 2022, 16(5): 675-690.
[25] JIN Guangyin, LIANG Yuxuan, FANG Yuchen, et al. Spatio-temporal graph neural networks for predictive learning in urban computing: a survey[J]. IEEE transactions on knowledge and data engineering, 2024, 36(10): 5388-5408.
[26] YU Bing, YIN Haoteng, ZHU Zhanxing. Spatio-temporal graph convolutional networks: a deep learning framework for traffic forecasting[C]//Proceedings of the 27th International Joint Conference on Artificial Intelligence. Freiburg: IJCAI, 2018: 3634-3640.
[27] GUO Shengnan, LIN Youfang, WAN Huaiyu, et al. Learning dynamics and heterogeneity of spatial-temporal graph data for traffic forecasting[J]. IEEE transactions on knowledge and data engineering, 2022, 34(11): 5415-5428.
[28] LI Yaguang, YU R, SHAHABI C, et al. Diffusion convolutional recurrent neural network: Data-driven traffic forecasting[EB/OL]. (2017-04-06)[2024-02-01]. https://arxiv.org/abs/1707.01926.
[29] BAI Lei, YAO Lina, LI Can, et al. Adaptive graph convolutional recurrent network for traffic forecasting[J]. IEEE internet of things journal, 2023, 10(13): 11465-11475.
[30] WU Zonghan, PAN Shirui, LONG Guodong, et al. Connecting the dots: multivariate time series forecasting with graph neural networks[C]//Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining. New York: ACM, 2020: 753-763.
[31] LI Fuxian, FENG Jie, YAN Huan, et al. Dynamic graph convolutional recurrent network for traffic prediction: benchmark and solution[J]. ACM transactions on knowledge discovery from data, 2023, 17(1): 1-21.
[32] KONG Weiyang, GUO Ziyu, LIU Yubao. Spatio-temporal pivotal graph neural networks for traffic flow forecasting[C]//Proceedings of the AAAI Conference on Artificial Intelligence, Palo Alto: AAAI, 2024: 8627-8635.
[33] CUI Yue, XIE Jiandong, ZHENG Kai. Historical inertia: a neglected but powerful baseline for long sequence time-series forecasting[C]//Proceedings of the 30th ACM International Conference on Information & Knowledge Management. New York: ACM, 2021: 2965-2969.
[34] HOCHREITER S, SCHMIDHUBER J. Long short-term memory[J]. Neural computation, 1997, 9(8): 1735-1780.
[35] FANG Yuchen, QIN Yanjun, LUO Haiyong, et al. When spatio-temporal meet wavelets: disentangled traffic forecasting via efficient spectral graph attention networks[C]//2023 IEEE 39th International Conference on Data Engineering. Anaheim: IEEE, 2023: 517-529.
[36] SHAO Zezhi, ZHANG Zhao, WEI Wei, et al. Decoupled dynamic spatial-temporal graph neural network for traffic forecasting[J]. Proceedings of the VLDB Endowment, 2022, 15(11): 2733-2746.
- 相似文献/References:
-
[1]李伯涵,郭茂祖,赵玲玲.基于分割注意力机制残差网络的城市区域客流量预测[J].智能系统学报,2022,17(4):839.[doi:10.11992/tis.202202014]
LI Bohan,GUO Maozu,ZHAO Lingling.Passenger flow prediction in urban areas based on residual networks with split attention mechanism[J].CAAI Transactions on Intelligent Systems,2022,17():839.[doi:10.11992/tis.202202014]
备注/Memo
收稿日期:2024-2-7。
基金项目:国家自然科学基金面上项目（61772249）.
作者简介:孟祥福，教授，博士，主要研究方向为top-k查询、时空大数据。主持国家自然科学基金项目2项、辽宁省各类基金项目4项。发表学术论文20余篇，出版学术专著2部。E-mail：marxi@126.com。;谢伟鹏，硕士，主要研究方向为交通流量预测、人工智能。E-mail：webvit@163.com。;崔江燕，硕士，主要研究方向为图嵌入、最短路径距离计算和恢复。E-mail：1315249764@qq.com。
通讯作者:孟祥福. E-mail：marxi@126.com
更新日期/Last Update:
1900-01-01