基于多尺度动态时空卷积网络的交通流速度预测

Traffic Speed Prediction Based on a Multi-Scale Dynamic Spatio-Temporal Convolutional Network

摘要

准确可靠的交通流速度预测对提升交通管理效率、缓解交通拥堵具有重要意义。为实现交通流速度的准确预测并深入挖掘复杂的动态时空关系，提出一种基于多尺度动态时空卷积网络的交通流速度预测模型（MDSTCN）。首先，在图卷积神经网络基础上，构建自适应静态空间邻接矩阵，并引入注意力机制捕捉交通流的方向性和动态交互，以挖掘复杂的动态空间关系；其次，采用多尺度膨胀卷积结构捕捉时间局部特征与长期变化趋势；最后，基于真实数据集完成模型训练与测试，并设计多种对比实验。结果表明，与最佳基线模型Graph WaveNet相比，MDSTCN的ERMS，EMA和EMAP均有所下降；其在15，30 min和60 min预测时间尺度上的误差波动幅度最小，凸显了模型在长期预测任务中的良好适应性和稳定性。

Abstract

Accurate and reliable traffic speed prediction is crucial for enhancing traffic management efficiency and alleviating traffic congestion. To improve traffic speed prediction accuracy and capture complex dynamic spatio-temporal dependencies in traffic data, this study proposes a traffic speed prediction model based on a multi-scale dynamic spatio-temporal convolutional network (MDSTCN). First, an adaptive static spatial adjacency matrix is constructed based on graph convolutional network (GCN), and an attention mechanism is introduced to capture the directional dependencies and dynamic interactions of traffic flow, thereby uncovering intricate dynamic spatial relationships. Second, a multi-scale dilated convolution structure is adopted to extract local temporal features and long-term variation trends. Finally, the model is trained and tested on a real-world dataset, and various comparative experiments are conducted. The results show that, compared with the best baseline model (Graph WaveNet) the proposed MDSTCN achieves lower ERMS, EMA, and EMAP. Furthermore, the fluctuation range of prediction errors across the 15, 30 min, and 60 min horizons are the smallest, highlighting its good adaptability and stability in long-term prediction tasks.

关键词

交通流速度预测 / 动态图卷积网络 / 多尺度膨胀卷积

Key words

traffic speed prediction / dynamic graph convolutional network / multi-scale dilated convolution

参考文献

[1] WANG S Z, CAO J N, YU P S . Deep learning for spatio—temporal data mining: a survey[J]. IEEE Transactions on Knowledge and Data Engineering, 2020, 34(8): 3681-3700.

[2] SMITH B L, DEMETSKY M J . Traffic flow forecasting: comparison of modeling approaches[J]. Journal of Transportation Engineering, 1997, 123(4): 261-266.

[3] 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.

[4] SUN S L, ZHANG C S, YU G Q . A Bayesian network approach to traffic flow forecasting[J]. IEEE Transactions on Intelligent Transportation Systems, 2006, 7(1): 124-132.

[5] LI L C, QU X, ZHANG J, et al. Traffic speed prediction for intelligent transportation system based on a deep feature fusion model[J]. Journal of Intelligent Transportation Systems, 2019, 23(6): 605-616.

[6] LINGRAS P, SHARMA S, ZHONG M . Prediction of recreational travel using genetically designed regression and time—delay neural network models[J]. Transportation Research Record: Journal of the Transportation Research Board, 2002, 1805(1): 16-24.

[7] FAN J, ZHANG K, HUANG Y P, et al. Parallel spatio—temporal attention—based TCN for multivariate time series prediction[J]. Neural Computing and Applications, 2023, 35(18): 13109-13118.

[8] MA C X, DAI G W, ZHOU J B . Short—term traffic flow prediction for urban road sections based on time series analysis and LSTM—BiLSTM method[J]. IEEE Transactions on Intelligent Transportation Systems, 2021, 23(6): 5615-5624.

[9] HUSSAIN B, AFZAL M K, AHMAD S, et al. Intelligent traffic flow prediction using optimized GRU model[J]. IEEE Access, 2021, 9: 100736-100746.

[10] ZHANG R J, SUN F, SONG Z W, et al. Short—term traffic flow forecasting model based on GA—TCN[J]. Journal of Advanced Transportation, 2021, 2021(1): 1338607.

[11] AKHTAR M, MORIDPOUR S . A review of traffic congestion prediction using artificial intelligence[J]. Journal of Advanced Transportation, 2021, 2021(1): 8878011.

[12] KE R M, LI W, CUI Z Y, et al. Two—stream multi—channel convolutional neural network for multi—lane traffic speed prediction considering traffic volume impact[J]. Transportation Research Record: Journal of the Transportation Research Board, 2020, 2674(4): 459-470.

[13] 王竟成, 张勇, 胡永利, 等 . 基于图卷积网络的交通预测综述[J]. 北京工业大学学报, 2021, 47(8): 954-970.

[14] WANG J C, ZHANG Y, HU Y L, et al. Survey on graph convolutional neural network—based traffic prediction[J]. Journal of Beijing University of Technology, 2021, 47(8): 954-970.

[15] 陈华伟, 邵毅明, 敖谷昌, 等 . 面向在线地图的GCN—LSTM神经网络速度预测[J]. 交通运输工程学报, 2021, 21(4): 183-196.

[16] CHEN H W, SHAO Y M, AO G C, et al. Speed prediction by online map—based GCN—LSTM neural network[J]. Journal of Traffic and Transportation Engineering, 2021, 21(4): 183-196.

[17] 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.

[18] MALLICK T, BALAPRAKASH P, RASK E, et al. Graph—partitioning—based diffusion convolutional recurrent neural network for large—scale traffic forecasting[J]. Transportation Research Record: Journal of the Transportation Research Board, 2020, 2674(9): 473-488.

[19] ZHANG Z K, LI Y D, SONG H F, et al. Multiple dynamic graph based traffic speed prediction method[J]. Neurocomputing, 2021, 461: 109-117.

[20] WANG Y, JING C F, XU S S, et al. Attention—based spatiotemporal graph attention networks for traffic flow forecasting[J]. Information Sciences, 2022, 607: 869-883.

[21] WANG Z H, DING D, LIANG X . TYRE: a dynamic graph model for traffic prediction[J]. Expert Systems with Applications, 2023, 215: 119311.

[22] 肖琳, 陈洪超, 邹复民 . 基于多头注意力时空图神经网络的交通流预测[J]. 重庆交通大学学报(自然科学版), 2024, 43(9): 78-85.

[23] XIAO L, CHEN H C, ZOU F M . Traffic flow prediction based on multi—head attention spatiotemporal graph neural network[J]. Journal of Chongqing Jiaotong University (Natural Science), 2024, 43(9): 78-85.

基金资助

江苏省自然科学基金项目(BK20211203)