面向交通流预测的全局-局部时空感知模型

doi:10.19678/j.issn.1000-3428.0069550

计算机工程 ›› 2026, Vol. 52 ›› Issue (3): 392-402. doi: 10.19678/j.issn.1000-3428.0069550

面向交通流预测的全局-局部时空感知模型

潘理虎¹^,*(), 尹佳莉¹, 张睿¹, 谢斌红¹, 张林梁²

1. 太原科技大学计算机科学与技术学院, 山西太原 030024
2. 山西省智慧交通研究院有限公司, 山西太原 030036

收稿日期:2024-03-13 修回日期:2024-06-04 出版日期:2026-03-15 发布日期:2024-09-24
通讯作者: 潘理虎
作者简介:
潘理虎(CCF高级会员), 男, 教授、博士, 主研方向为人工智能、领域软件工程
尹佳莉, 硕士研究生
张睿(CCF高级会员), 副教授、博士
谢斌红(CCF会员), 教授
张林梁, 高级工程师、博士
基金资助:
山西省基础研究项目(202203021221145); 山西省研究生联合培养示范基地项目(2022JD11)

Global-Local Spatiotemporal Perception Model for Traffic Flow Prediction

PAN Lihu¹^,*(), YIN Jiali¹, ZHANG Rui¹, XIE Binhong¹, ZHANG Linliang²

1. College of Computer Science and Technology, Taiyuan University of Science and Technology, Taiyuan 030024, Shanxi, China
2. Shanxi Intelligent Transportation Institute Co., Ltd., Taiyuan 030036, Shanxi, China

Received:2024-03-13 Revised:2024-06-04 Online:2026-03-15 Published:2024-09-24
Contact: PAN Lihu

摘要/Abstract

摘要：

交通流预测方法是智能交通系统的重要基础, 但现有方法在准确捕获交通数据的时空相关性上仍有不足。为挖掘道路网络的复杂时空相关性, 提高预测性能, 提出一种考虑全局-局部时空感知的时空图注意力网络模型GL-STAGGN。首先对输入数据进行时空位置嵌入来表征交通流的时空异质性, 以增强时空数据的特征表示, 其次利用全局-局部时间感知的多头自注意力同步挖掘全局与局部空间范围内的时间动态相关性; 然后引入图注意力网络和基于注意力机制的动态图卷积网络分别聚合局部节点特征和动态调整空间相关性强度, 以深度捕捉全局与局部空间相关性的内在关联; 最后采用编码器-解码器架构将时空组件融合以构成GL-STAGGN模型。在现实世界的高速公路交通数据集PEMS04和PEMS08上的实验结果表明, 相比未考虑全局-局部时空关系和忽略空间异质性的先进方法DSTAGNN, GL-STAGGN的平均绝对误差(MAE)、均方根误差(RMSE)和平均绝对百分比误差(MAPE)平均降低了2.8%、2.3%和3.3%, 优于大多数现有基线模型, 可更好地为智能交通系统提供支持。

Abstract:

Traffic flow prediction is crucial for intelligent transportation systems; however, the existing methods cannot accurately capture the temporal and spatial correlation of traffic data. To further explore the complex spatiotemporal correlation of road networks and improve prediction performance, a spatiotemporal graph attention network GL-STAGGN model considering global-local spatiotemporal perception is proposed. First, the spatiotemporal heterogeneity of traffic flow is represented by embedding the spatiotemporal location of the input data to enhance the feature representation of spatiotemporal data; subsequently, global-local time-aware multi-head self-attention synchronization is used to mine the global and local spatiotemporal dynamic correlation. Second, a graph attention network and a dynamic graph convolutional network based on the attention mechanism are introduced to aggregate local node features and dynamically adjust the spatial correlation intensity for capturing the internal correlation between global and local spatial correlations in depth. Finally, the GL-STAGGN model is constructed using an encoder-decoder architecture to fuse the spatiotemporal components. Experimental results on real-world highway traffic datasets, PEMS04 and PEMS08, show that compared with the advanced method DSTAGNN, which does not consider the global-local spatiotemporal relationship and spatial heterogeneity, the average Mean Absolute Error (MAE), Root Mean Square Error (RMSE), and Mean Absolute Percentage Error (MAPE) decreased by 2.8%, 2.3%, and 3.3%, respectively. Furthermore, GL-STAGGN performs better than most existing baseline models in terms of supporting intelligent transportation systems.

Key words: traffic flow prediction, spatio-temporal correlation, encoder-decoder, attention mechanism, dynamic graph convolution network

潘理虎, 尹佳莉, 张睿, 谢斌红, 张林梁. 面向交通流预测的全局-局部时空感知模型[J]. 计算机工程, 2026, 52(3): 392-402.

PAN Lihu, YIN Jiali, ZHANG Rui, XIE Binhong, ZHANG Linliang. Global-Local Spatiotemporal Perception Model for Traffic Flow Prediction[J]. Computer Engineering, 2026, 52(3): 392-402.

https://www.ecice06.com/CN/Y2026/V52/I3/392

图/表 9

图1 基于编码器-解码器架构的GL-STAGGN模型

Fig.1 GL-STAGGN model based on encoder-decoder architecture

图2 全局-局部时间感知多头自注意力

Fig.2 Global-local time perception multi-head self-attention

图3 空间DGCN

Fig.3 Spatial DGCN

图4 GL-STAGGN的成分分析

Fig.4 Composition analysis of GL-STAGGN

图5 GL-STAGGN在预测12个时间步上的成分分析

Fig.5 Component analysis of GL-STAGGN in predicting 12 time steps

图6 不同网络配置对模型性能的影响

Fig.6 Impact of different network configurations on model performance

参考文献 42

1	周玮, 闵卫东. 面向交通场景的强鲁棒性场景图生成网络. 计算机工程, 2025, 51 (9): 231- 241. doi: 10.19678/j.issn.1000-3428.0069154
	ZHOU W , MIN W D . Robust scene graph generation network for traffic scenes. Computer Engineering, 2025, 51 (9): 231- 241. doi: 10.19678/j.issn.1000-3428.0069154
2	JIN G Y , LIANG Y X , FANG Y C , et al. Spatio-temporal graph neural networks for predictive learning in urban computing: a survey. IEEE Transactions on Knowledge and Data Engineering, 2023, 36 (10): 5388- 5408.
3	WILLIAMS B M , HOEL L A . Modeling and forecasting vehicular traffic flow as a seasonal ARIMA process: theoretical basis and empirical results. Journal of Transportation Engineering, 2003, 129 (6): 664- 672. doi: 10.1061/(ASCE)0733-947X(2003)129:6(664)
4	ZIVOT E , WANG J . Vector autoregressive models for multivariate time series. Berlin, Germany: Springer, 2006.
5	OKUTANI I , STEPHANEDES Y J . Dynamic prediction of traffic volume through Kalman filtering theory. Transportation Research Part B: Methodological, 1984, 18 (1): 1- 11. doi: 10.1016/0191-2615(84)90002-X
6	WU C H , HO J M , LEE D T . Travel-time prediction with support vector regression. IEEE Transactions on Intelligent Transportation Systems, 2004, 5 (4): 276- 281. doi: 10.1109/TITS.2004.837813
7	VAN L J W C , VAN H C . Short-term traffic and travel time prediction models. Artificial Intelligence Applications to Critical Transportation Issues, 2012, 22 (1): 22- 41.
8	YU B, YIN H T, ZHU Z X. Spatio-temporal graph convolutional networks: a deep learning framework for traffic forecasting[EB/OL]. [2024-02-10]. https://arxiv.org/pdf/1709.04875.
9	LI Y G, YU R, SHAHABI C, et al. Diffusion convolutional recurrent neural network: data-driven traffic forecasting[EB/OL]. [2024-02-10]. https://arxiv.org/pdf/1707.01926.
10	GUO S N , LIN Y F , FENG N , et al. Attention based spatial-temporal graph convolutional networks for traffic flow forecasting. Artificial Intelligence, 2019, 33 (1): 922- 929.
11	ZHENG C P , FAN X L , WANG C , et al. GMAN: a graph multi-attention network for traffic prediction. Artificial Intelligence, 2020, 34 (1): 1234- 1241.
12	SONG C , LIN Y F , GUO S N , et al. Spatial-temporal synchronous graph convolutional networks: a new framework for spatial-temporal network data forecasting. Artificial Intelligence, 2020, 34 (1): 914- 921.
13	LI M Z , ZHU Z X . Spatial-temporal fusion graph neural networks for traffic flow forecasting. Artificial Intelligence, 2021, 35 (5): 4189- 4196.
14	LAN S Y, MA Y T, HUANG W, et al. DSTAGNN: dynamic spatial-temporal aware graph neural network for traffic flow forecasting[C]//Proceedings of International Conference on Machine Learning. Washington D. C., USA: IEEE Press, 2022: 11906-11917.
15	LUO X L, ZHU C J, ZHANG D T, et al. Dynamic graph convolution network with spatio-temporal attention fusion for traffic flow prediction[EB/OL]. [2024-02-10]. https://arxiv.org/pdf/2310.08328.
16	周楚昊, 林培群. 基于多通道Transformer的交通量预测方法. 计算机应用研究, 2023, 40 (2): 435- 439.
	ZHOU C H , LIN P Q . Traffic flow prediction method based on multi-channel Transformer. Application Research of Computers, 2023, 40 (2): 435- 439.
17	XU X, ZHANG L, LIU B L, et al. Transport-hub-aware spatial-temporal adaptive graph Transformer for traffic flow prediction[EB/OL]. [2024-02-10]. https://arxiv.org/pdf/2310.08328.
18	LIU A Y, ZHANG Y Y. Spatial-temporal interactive dynamic graph convolution network for traffic forecasting[EB/OL]. [2024-02-10]. https://arxiv.org/pdf/2205.08689.
19	FU R, ZHANG Z, LI L. Using LSTM and GRU neural network methods for traffic flow prediction[C]//Proceedings of the 31st Youth Academic Annual Conference of Chinese Association of Automation. Wuhan, China: [s. n. ], 2016: 324-328.
20	CHO K, MERRIENBOER B V, GÜLÇEHRE Ç, et al. Learning phrase representations using RNN encoder-decoder for statistical machine translation[EB/OL]. [2024-02-10]. https://arxiv.org/pdf/1406.1078.
21	CUI Z Y , KE R M , PU Z Y , et al. Stacked bidirectional and unidirectional LSTM recurrent neural network for forecasting network-wide traffic state with missing values. Transportation Research Part C: Emerging Technologies, 2020, 118, 102674. doi: 10.1016/j.trc.2020.102674
22	MA X L , TAO Z M , WANG Y H , et al. Long short-term memory neural network for traffic speed prediction using remote microwave sensor data. Transportation Research Part C: Emerging Technologies, 2015, 54, 187- 197. doi: 10.1016/j.trc.2015.03.014
23	倪庆剑, 彭文强, 张志政, 等. 基于信息增强传输的时空图神经网络交通流预测. 计算机研究与发展, 2022, 59 (2): 282- 293.
	NI Q J , PENG W Q , ZHANG Z Z , et al. Spatial-temporal graph neural network for traffic flow prediction based on information enhanced transmission. Journal of Computer Research and Development, 2022, 59 (2): 282- 293.
24	CUI Z, KE R, PU Z, et al. Deep bidirectional and unidirectional LSTM recurrent neural network for network-wide traffic speed prediction[EB/OL]. [2024-02-10]. https://arxiv.org/pdf/1801.02143.
25	VAN DEN OORD A, DIELEMAN S, ZEN H, et al. WaveNet: a generative model for raw audio[EB/OL]. [2024-02-10]. https://arxiv.org/pdf/1609.03499.
26	BAI S, KOLTER J Z, KOLTUN V. An empirical evaluation of generic convolutional and recurrent networks for sequence modeling[EB/OL]. [2024-02-10]. https://arxiv.org/pdf/1803.01271.
27	ZHANG J B , ZHENG Y , QI D K . Deep spatio-temporal residual networks for citywide crowd flows prediction. Artificial Intelligence, 2017, 31 (1): 332- 343.
28	YAO H X , TANG X F , WEI H , et al. Revisiting spatial-temporal similarity: a deep learning framework for traffic prediction. Artificial Intelligence, 2019, 33 (1): 5668- 5675.
29	HUANG R, HUANG C, LIU Y, et al. LSGCN: long short-term traffic prediction with graph convolutional networks[C]//Proceedings of the IJCAI'20. Washington D. C., USA: IEEE Press, 2020: 2355-2361.
30	ZHAO Y J , LIN Y F , WEN H M , et al. Spatial-temporal position-aware graph convolution networks for traffic flow forecasting. IEEE Transactions on Intelligent Transportation Systems, 2022, 24 (8): 8650- 8666.
31	CIRSTEA R G, YANG B, GUO C J, et al. Towards spatio- temporal aware traffic time series forecasting[C]//Proceedings of the 38th IEEE International Conference on Data Engineering. Washington D. C., USA: IEEE Press, 2022: 2900-2913.
32	LIU H Y , ZHU C J , ZHANG D T , et al. Attention-based spatial-temporal graph convolutional recurrent networks for traffic forecasting. Berlin, Germany: Springer, 2023.
33	WU Z, PAN S, LONG G, et al. Graph wavenet for deep spatial-temporal graph modeling[EB/OL]. [2024-02-10]. https://arxiv.org/pdf/1906.00121.
34	ZHANG W Y , ZHU K , ZHANG S , et al. Dynamic graph convolutional networks based on spatiotemporal data embedding for traffic flow forecasting. Knowledge-Based Systems, 2022, 250, 109028. doi: 10.1016/j.knosys.2022.109028
35	KONG J L , FAN X M , ZUO M , et al. ADCT-Net: adaptive traffic forecasting neural network via dual-graphic cross-fused transformer. Information Fusion, 2024, 103, 102122. doi: 10.1016/j.inffus.2023.102122
36	BUI K N , CHO J , YI H . Spatial-temporal graph neural network for traffic forecasting: an overview and open research issues. Applied Intelligence, 2022, 52 (3): 2763- 2774. doi: 10.1007/s10489-021-02587-w
37	VASWANI A, SHAZEER N, PARMAR N, et al. Attention is all you need[C]//Proceedings of Advances in Neural Information Processing Systems. Cambridge, USA: MIT Press, 2017: 303-315.
38	BELKIN M, NIYOGI P. Laplacian eigenmaps and spectral techniques for embedding and clustering[C]//Proceedings of Advances in Neural Information Processing Systems. Cambridge, USA: MIT Press, 2002: 585-592.
39	WANG K F , AN J , ZHOU M C , et al. Minority-weighted graph neural network for imbalanced node classification in social networks of Internet of people. IEEE Internet of Things Journal, 2022, 10 (1): 330- 340.
40	YE Y Q , XIAO Y , ZHOU Y X , et al. Dynamic multi-graph neural network for traffic flow prediction incorporating traffic accidents. Expert Systems with Applications, 2023, 234, 121101. doi: 10.1016/j.eswa.2023.121101
41	GUO S N , LIN Y F , WAN H Y , et al. Learning dynamics and heterogeneity of spatial-temporal graph data for traffic forecasting. IEEE Transactions on Knowledge and Data Engineering, 2021, 34 (11): 5415- 5428.
42	STEPHANEDES Y , MICHALOPOULOS P , PLUM R . Comparative performance evaluation of demand and prediction algorithms. Traffic Engineering & Control, 1981, 22 (32): 443- 452.

[1]	吴雪松, 陈媛媛, 周涛. 基于多尺度金字塔池化的自适应无参考图像质量评价[J]. 计算机工程, 2026, 52(3): 107-118.
[2]	刘啸宇, 廖志芳, 谈遂, 余志武. 基于堆叠GRU神经网络的桥梁动应变预测[J]. 计算机工程, 2026, 52(3): 441-450.
[3]	苏建华, 池云仙, 许云峰, 高凯. 基于注意力模态融合的多模态意图识别[J]. 计算机工程, 2026, 52(3): 234-242.
[4]	顾群, 随思懿, 王瑞, 张海, 许天鹏. 基于改进YOLOv8的皮肤黑色素瘤图像分割算法[J]. 计算机工程, 2026, 52(3): 429-440.
[5]	曹继卫, 罗飞, 丁炜超. BS-YOLO: 基于BSAM注意力机制和SCConv的小目标检测算法[J]. 计算机工程, 2026, 52(3): 119-127.
[6]	陈国莲, 冯梓洋, 曹均阔. 基于多模态空间特征融合的网络欺凌检测研究[J]. 计算机工程, 2026, 52(3): 255-263.
[7]	李健浪, 吴新电, 陈灵, 阳波, 唐文胜. 基于4D毫米波雷达与视觉融合的三维目标检测算法[J]. 计算机工程, 2026, 52(2): 299-310.
[8]	张信佳, 王芳. 基于多层次特征融合和注意力机制的无人机图像小目标检测算法[J]. 计算机工程, 2026, 52(2): 148-157.
[9]	但崇鸿, 韦洪雷, 何舟, 吴贯锋. SRMpose: 一种多尺度特征提取的关键点检测算法[J]. 计算机工程, 2026, 52(2): 136-147.
[10]	文浪, 苟光磊, 白瑞峰, 缪宛谕. 基于邻域融合和特征增强的小样本细粒度图像分类[J]. 计算机工程, 2026, 52(2): 158-166.
[11]	宋朝琦, 刘颖, 何敬鲁, 李大湘. 基于显著位置交互Transformer的小样本图像分类方法[J]. 计算机工程, 2026, 52(2): 167-176.
[12]	王庆荣, 郝福乐, 朱昌锋, 王俊杰. 基于多特征融合的车辆轨迹预测研究[J]. 计算机工程, 2026, 52(2): 331-341.
[13]	刘畅, 梁冰雪, 田荣坤, 秦玉华. 基于多特征融合和混合神经网络的医疗健康问题分类[J]. 计算机工程, 2026, 52(2): 342-355.
[14]	许晓阳, 魏伟, 高重阳. 基于改进YOLOv7-tiny的红外船舶目标检测[J]. 计算机工程, 2026, 52(2): 209-220.
[15]	薛阳, 秦瑶, 张舒翔. 基于双重图注意力网络生成子图的图神经协同推荐[J]. 计算机工程, 2026, 52(2): 89-100.

选择文件类型/文献管理软件名称

选择包含的内容

面向交通流预测的全局-局部时空感知模型

Global-Local Spatiotemporal Perception Model for Traffic Flow Prediction

RichHTML

PDF

可视化

被引次数

摘要/Abstract

引用本文

使用本文

图/表 9

参考文献 42

相关文章 15

编辑推荐

Metrics

本文评价

模态框（Modal）标题

选择文件类型/文献管理软件名称

选择包含的内容

面向交通流预测的全局-局部时空感知模型

Global-Local Spatiotemporal Perception Model for Traffic Flow Prediction

RichHTML

PDF

可视化

被引次数

摘要/Abstract

引用本文

使用本文

图/表 9

参考文献 42

相关文章 15

编辑推荐

Metrics

本文评价