城市交通拥堵预测研究：以西安市为例

doi:10.3778/j.issn.1002-8331.2407-0100

摘要/Abstract

摘要： 随着经济的发展和生活水平的提升，出行旅游逐渐成为流行的休闲方式，尤其在国庆等假日期间。然而，集中的出行需求引起的城市交通拥堵问题，不仅影响出行效率和体验，也加大了城市运行压力。该研究以西安市为例，深入分析假日期间的交通拥堵模式和特征，提出了一种基于深度学习拥堵预测模型ConstFormer。该模型融合了图卷积网络（graph convolutional network）和Transformer架构，利用图卷积网络探索空间邻接关系，以及Transformer的自注意力机制来挖掘长时空依赖关系，从而有效预测未来的交通状况。对比实验表明，ConstFormer模型对比基线模型均取得了最佳的性能，能够为人们规避高峰期和合理安排出行提供帮助。

关键词: 拥堵预测, 数据分析, 城市交通, 图卷积网络, Transformer

Abstract: With the development of the economy and the improvement of living standards, traveling and tourism have gradually become a popular way of leisure, especially during the National Day and other holidays. However, urban traffic congestion caused by concentrated travel demand not only affects travel efficiency and experience, but also increases the pressure of urban operation. This study takes Xi’an as an example to deeply analyze the traffic congestion patterns and characteristics during the holiday period, and proposes a deep learning-based congestion prediction model, ConstFormer.The model integrates the graph convolutional network (GCN) and Transformer architectures, which explores spatial adjacencies using the GCN, and the Transformer’s self-attention mechanism to mine long spatial and temporal dependencies to effectively predict future traffic conditions. Comparison experiments show that the ConstFormer model achieves the best performance over the baseline model, which can help people avoid peak periods and rationalize their travel arrangements.

Key words: congestion prediction, data analysis, urban transportation, graph convolutional network (GCN), Transformer

颜建强, 张霖, 高原, 李银香. 城市交通拥堵预测研究：以西安市为例[J]. 计算机工程与应用, 2025, 61(1): 330-340.

YAN Jianqiang, ZHANG Lin, GAO Yuan, LI Yinxiang. Urban Traffic Congestion Prediction Study： Case Study of Xi’an City[J]. Computer Engineering and Applications, 2025, 61(1): 330-340.

参考文献

[1] NG M K, ZHAI B, ZHAO Y, et al. Valuing Xi’an: a Chinese capital city for 13 dynasties[J]. DisP-the Planning Review, 2016, 52(3): 8-15.
[2] BARTH M, BORIBOONSOMSIN K. Traffic congestion and greenhouse gases[J]. Access Magazine, 2009, 1(35): 2-9.
[3] SHI K, DI B, ZHANG K, et al. Detrended cross-correlation analysis of urban traffic congestion and NO2 concentrations in Chengdu[J]. Transportation Research Part D: Transport and Environment, 2018, 61: 165-173.
[4] AFRIN T, YODO N. A survey of road traffic congestion measures towards a sustainable and resilient transportation system[J]. Sustainability, 2020, 12(11): 4660.
[5] WU K, CHEN Y, MA J, et al. Traffic and emissions impact of congestion charging in the central Beijing urban area: a simulation analysis[J]. Transportation Research Part D: Transport and Environment, 2017, 51: 203-215.
[6] CHOUDHARY A, GOKHALE S. Urban real-world driving traffic emissions during interruption and congestion[J]. Transportation Research Part D: Transport and Environment, 2016, 43: 59-70.
[7] LUAN M, WALLER S T, REY D. A non-additive path-based reward credit scheme for traffic congestion management[J]. Transportation Research Part E: Logistics and Transportation Review, 2023, 179: 103291.
[8] TSEKERIS T, GEROLIMINIS N. City size, network structure and traffic congestion[J]. Journal of Urban Economics, 2013, 76: 1-14.
[9] AFTABUZZAMAN M. Measuring traffic congestion-a critical review[C]//Proceedings of the 30th Australasian Transport Research Forum, 2007.
[10] JAIN V, SHARMA A, SUBRAMANIAN L, et al. Road traffic congestion in the developing world[C]//Proceedings of the 2nd ACM Symposium on Computing for Development. New York: ACM, 2012: 1-10.
[11] HUANG G, XU D. The last mile matters: impact of dockless bike-sharing services on traffic congestion[J]. Transportation Research Part D: Transport and Environment, 2023, 121: 103836.
[12] AKHTAR M, MORIDPOUR S. A review of traffic congestion prediction using artificial intelligence[J]. Journal of Advanced Transportation, 2021, 2021(1): 8878011.
[13] LEE S, FAMBRO D B. Application of subset autoregressive integrated moving average model for short-term freeway traffic volume forecasting[J]. Transportation Research Record: Journal of the Transportation Research Board, 1999, 1678(1): 179-188.
[14] WILLIAMS B M. Multivariate vehicular traffic flow prediction: evaluation of ARIMAX modeling[J]. Transportation Research Record: Journal of the Transportation Research Board, 2001, 1776(1): 194-200.
[15] 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.
[16] KAMARIANAKIS Y, PRASTACOS P. Space-time modeling of traffic flow[J]. Computers & Geosciences, 2005, 31(2): 119-133.