Research on Highway Traffic Congestion Prediction Based on SA-GFSTCN

doi:10.19678/j.issn.1000-3428.0070026

Abstract

Abstract:

Existing traffic congestion prediction methodologies are based on simplistic definitions of congestion indices and fail to effectively integrate static—adaptive graph information. To address these issues, this paper proposes an innovative Traffic Congestion Index (TCI), and a novel traffic congestion prediction model based on static-adaptive graph fusion called SA-GFSTCN. The TCI is defined based on three metrics, namely average speed, traffic flow, and occupancy rate, which collectively reflect road usage and traffic conditions. The model employs a parallel architecture to process the input data using spatiotemporal convolution and spatiotemporal attention modules to model the static road network structure and extract fixed structural information along with the spatiotemporal characteristics. Concurrently, adaptive graph convolution and gated temporal convolution are used to process adaptive graph data and extract dynamic spatiotemporal associative features. Finally, a cross-attention mechanism effectively fuses the outputs of the adaptive graph convolution and gated temporal convolution. Experiments conducted on two real-world traffic datasets demonstrate that the SA-GFSTCN model outperforms the optimal baseline model in terms of Mean Absolute Error (MAE), Mean Absolute Percentage Error (MAPE), and Root Mean Square Error (RMSE). Specifically, it achieves improvements of 0.27 and 0.20 in MAE, 0.22 and 0.23 percentage points in MAPE, and 0.38 and 0.36 in RMSE, respectively, across the datasets when compared to the baseline model. These results validate the effectiveness of the proposed model.

Key words: traffic congestion prediction, Traffic Congestion Index (TCI), static—adaptive graph fusion, adaptive graph convolution, cross attention

摘要：

针对现有交通拥堵预测方法中拥堵指数定义单一、静态-自适应图信息无法有效融合的问题, 设计一种创新的交通拥堵指数(TCI), 并提出基于静态-自适应图融合的交通拥堵预测模型——SA-GFSTCN。首先, 根据平均速度、交通流量和时间占有率3项指标反映的道路使用情况和交通流状况, 定义TCI; 然后, 模型采用并行架构处理输入数据, 使用时空卷积和时空注意力模块对静态路网结构进行处理, 提取固定的结构性信息及其时空特征; 接着, 采用自适应图卷积和门控时间卷积处理自适应图数据, 并提取动态的时空关联特征; 最后, 通过交叉注意力机制将这两部分输出进行有效融合。在2个真实的交通数据集上的实验结果表明, SA-GFSTCN模型在平均绝对误差(MAE)、平均绝对百分比误差(MAPE)、均方根误差(RMSE)3项指标上相较于最优基线模型分别提升了0.27与0.20、0.22与0.23百分点、0.38与0.36, 验证了SA-GFSTCN模型的有效性。

关键词: 交通拥堵预测, 交通拥堵指数, 静态-自适应图融合, 自适应图卷积, 交叉注意力

WANG Qingrong, GAO Huanyi, ZHU Changfeng, WANG Junjie. Research on Highway Traffic Congestion Prediction Based on SA-GFSTCN[J]. Computer Engineering, 2026, 52(4): 446-456.

王庆荣, 高桓伊, 朱昌锋, 王俊杰. 基于SA-GFSTCN的高速公路交通拥堵预测研究[J]. 计算机工程, 2026, 52(4): 446-456.

/ Recommend / Download Citations

URL: https://www.ecice06.com/EN/10.19678/j.issn.1000-3428.0070026

https://www.ecice06.com/EN/Y2026/V52/I4/446

Figures/Tables 18

Fig.1 Overall architecture of the SA-GFSTCN model

Fig.2 Spatio-temporal convolutional layer structure

Fig.3 Directed graph convolutional structure

Fig.4 Dilated causal convolution

Fig.5 Muti-heads graph attention mechanism

Fig.6 Muti-heads self-attention mechanism

Fig.7 Adaptive graph spatio-temporal convolution module structure

Fig.8 Comparison of original TCI and improved TCI calculation results

Fig.9 SG filter denoising effect

Fig.10 Impact of Batch Size on model performance

Fig.11 Impact of number of attention heads on model performance

Fig.12 Impact of graph convolution hidden layer dimensions on model performance

Fig.13 Comparison of prediction between SA-GFSTCN and Graph WaveNet

Fig.14 SA-GFSTCN ablation experimental results

References 26

1	LI L C, DAI F, HUANG B, et al. AST3DRNet: attention-based spatio-temporal 3D residual neural networks for traffic congestion prediction. Sensors, 2024, 24(4): 1261. doi: 10.3390/s24041261
2	XIAO X P, DUAN H M. A new grey model for traffic flow mechanics. Engineering Applications of Artificial Intelligence, 2020, 88, 103350. doi: 10.1016/j.engappai.2019.103350
3	SHAHRIARI S, GHASRI M, SISSON S A, et al. Ensemble of ARIMA: combining parametric and bootstrapping technique for traffic flow prediction. Transportmetrica A: Transport Science, 2020, 16(3): 1552- 1573. doi: 10.1080/23249935.2020.1764662
4	LIN X F, HUANG Y Z. Short-term high-speed traffic flow prediction based on ARIMA-GARCH-M model. Wireless Personal Communications, 2021, 117(4): 3421- 3430. doi: 10.1007/s11277-021-08085-z
5	ZHANG Z H, HAN Y, PENG T X, et al. A comprehensive spatio-temporal model for subway passenger flow prediction. ISPRS International Journal of Geo-Information, 2022, 11(6): 341. doi: 10.3390/ijgi11060341
6	梁艳平, 毛政元, 邹为彬, 等. 基于相似数据聚合与变K值KNN的短时交通流量预测. 地球信息科学学报, 2018, 20(10): 1403- 1411. doi: 10.12082/dqxxkx.2018.180281
	LIANG Y P, MAO Z Y, ZOU W B, et al. Short-term traffic flow prediction based on similar data aggregation and KNN with varying K-value. Journal of Geo-Information Science, 2018, 20(10): 1403- 1411. doi: 10.12082/dqxxkx.2018.180281
7	LUO J. Short-term traffic flow prediction method in Bayesian networks based on quantile regression. Promet-Traffic & Transportation, 2020, 32(6): 821- 835. doi: 10.7307/PTT.V32I6.3394
8	TOAN T D, TRUONG V H. Support vector machine for short-term traffic flow prediction and improvement of its model training using nearest neighbor approach. Transportation Research Record: Journal of the Transportation Research Board, 2021, 2675(4): 362- 373. doi: 10.1177/0361198120980432
9	LIN G C, LIN A J, GU D L. Using support vector regression and k-nearest neighbors for short-term traffic flow prediction based on maximal information coefficient. Information Sciences, 2022, 608, 517- 531. doi: 10.1016/j.ins.2022.06.090
10	姚俊峰, 何瑞, 史童童, 等. 基于机器学习的交通流预测方法综述. 交通运输工程学报, 2023, 23(3): 44- 67. doi: 10.19818/j.cnki.1671-1637.2023.03.003
	YAO J F, HE R, SHI T T, et al. Review on machine learning-based traffic flow prediction methods. Journal of Traffic and Transportation Engineering, 2023, 23(3): 44- 67. doi: 10.19818/j.cnki.1671-1637.2023.03.003
11	梁秀霞, 夏曼曼, 何月阳, 等. 基于时空多头图注意力网络的交通流预测. 电子学报, 2024, 52(2): 500- 509. doi: 10.12263/DZXB.20230474
	LIANG X X, XIA M M, HE Y Y, et al. Traffic flow prediction based on spatio-temporal multi-head graph attention network. Acta Electronica Sinica, 2024, 52(2): 500- 509. doi: 10.12263/DZXB.20230474
12	ZHU L, KRISHNAN R, GUO F C, et al. Early identification of recurrent congestion in heterogeneous urban traffic[C]// Proceedings of the IEEE Intelligent Transportation Systems Conference (ITSC). Washington D.C., USA: IEEE Press, 2019: 4392-4397.
13	户佐安, 邓锦程, 韩金丽, 等. 图神经网络在交通预测中的应用综述. 交通运输工程学报, 2023, 23(5): 39- 61. doi: 10.19818/j.cnki.1671-1637.2023.05.003
	HU Z A, DENG J C, HAN J L, et al. Review on application of graph neural network in traffic prediction. Journal of Traffic and Transportation Engineering, 2023, 23(5): 39- 61. doi: 10.19818/j.cnki.1671-1637.2023.05.003
14	YU B, YIN H T, ZHU Z X. Spatio-temporal graph convolutional networks: a deep learning framework for traffic forecasting[C]//Proceedings of the 27th International Joint Conference on Artificial Intelligence. Stockholm, Sweden: International Joint Conferences on Artificial Intelligence Organization, 2018: 3634-3640.
15	WU Z H, PAN S R, LONG G D, et al. Graph WaveNet for deep spatial-temporal graph modeling[C]//Proceedings of the 28th International Joint Conference on Artificial Intelligence. Macao, China: International Joint Conferences on Artificial Intelligence Organization, 2019: 1907-1913.
16	LI Y, YU R, SHAHABI C, et al. Diffusion convolu-tional recurrent neural network: data-driven traffic forecasting[EB/OL]. [2024-02-25]. https://arxiv.org/abs/1707.01926.
17	史昕, 曹凤腾, 纪艺, 等. 基于多尺度时空特征与软注意力机制的交通流预测方法. 计算机工程, 2024, 50(12): 346- 357. doi: 10.19678/j.issn.1000-3428.0068659
	SHI X, CAO F T, JI Y, et al. Traffic flow prediction method based on multi-scale spatio-temporal features and soft attention mechanism. Computer Engineering, 2024, 50(12): 346- 357. doi: 10.19678/j.issn.1000-3428.0068659
18	ZHANG C, WU Y, SHEN Y, et al. Adaptive graph convolutional recurrent network with transformer and whale optimization algorithm for traffic flow prediction. Mathematics, 2024, 12(10): 1493. doi: 10.3390/math12101493
19	龚循强, 邱万锦, 吕开云, 等. 变分模态分解与自适应图卷积门控循环网络的交通流量组合预测模型. 武汉大学学报(信息科学版), 2024, 49(12): 2329- 2341. doi: 10.13203/j.whugis20230249
	GONG X Q, QIU W J, LÜ K Y, et al. A combined traffic flow prediction model based on variational mode decomposition and adaptive graph convolutional gated recurrent network. Geomatics and Information Science of Wuhan University, 2024, 49(12): 2329- 2341. doi: 10.13203/j.whugis20230249
20	WANG X, ZENG R H, ZOU F M, et al. STTF: an efficient transformer model for traffic congestion prediction. International Journal of Computational Intelligence Systems, 2023, 16(1): 2. doi: 10.1007/s44196-022-00177-3
21	ZHANG Y L, SHANG K, CUI Z W, et al. Research on traffic flow prediction at intersections based on DT-TCN-attention. Sensors, 2023, 23(15): 6683. doi: 10.3390/s23156683
22	ZHANG Y Z, LIU S X, ZHANG P, et al. GRU- and Transformer-based periodicity fusion network for traffic forecasting. Electronics, 2023, 12(24): 4988. doi: 10.3390/electronics12244988
23	胡杰, 龚永胜, 蔡世杰, 等. 基于多源数据的车流量时空预测方法. 汽车工程, 2021, 43(11): 1662- 1672. doi: 10.19562/j.chinasae.qcgc.2021.11.012
	HU J, GONG Y S, CAI S J, et al. A spatio-temporal prediction method of traffic flow based on multi-source data. Automotive Engineering, 2021, 43(11): 1662- 1672. doi: 10.19562/j.chinasae.qcgc.2021.11.012
24	Caltrans performance measurement system[EB/OL]. [2024-02-25]. http://pems.dot.ca.gov/.
25	WANG Q R, CHEN X H. Short-term traffic flow prediction based on the SGA-KGCN-LSTM model[EB/OL]. [2024-02-25]. https://www.engineeringletters.com/issues_v31/issue_3/EL_31_3_36.pdf.
26	SMITH B L, WILLIAMS B M, OSWALD R K. Comparison of parametric and nonparametric models for traffic flow forecasting. Transportation Research Part C: Emerging Technologies, 2002, 10(4): 303- 321. doi: 10.1016/S0968-090X(02)00009-8

[1]	YANG Yuxue, HE Tian, FAN Jinghang, LIU Ruiying, LI Teng. Research on Cross-Modal Image-Text Retrieval Based on Cross Attention and Feature Aggregation [J]. Computer Engineering, 2026, 52(2): 311-321.
[2]	LI Jianlang, WU Xindian, CHEN Ling, YANG Bo, TANG Wensheng. 3D Object Detection Algorithm Based on 4D Millimeter-Wave Radar and Vision Fusion [J]. Computer Engineering, 2026, 52(2): 299-310.
[3]	ZOU Shaohua, LIU Xiaozhang, LI Xiulai. Infrared Ship Target Detection Model Integrating Criss-Cross Attention and Dual Feature Interaction [J]. Computer Engineering, 2026, 52(1): 390-399.
[4]	Yiwen ZHANG, Manchun CAI, Yonghao CHEN, Yi ZHU, Lifeng YAO. Multi-Scale Deepfake Detection Method with Fusion of Spatial Features [J]. Computer Engineering, 2024, 50(7): 240-250.
[5]	Kuan WANG, Shibin XUAN, Xuedong HE, Ziwei LI, Jiaxiang LI. Human Pose Estimation Method Based on Cross Attention Transformer [J]. Computer Engineering, 2023, 49(7): 223-231.
[6]	Wenli ZHANG, Lan CHENG, Mifeng REN, Xinying XU, Gaowei YAN, Zhe ZHANG. Point Cloud Registration Based on AGConv Local Feature Descriptors [J]. Computer Engineering, 2023, 49(11): 231-237.
[7]	Zijun ZHANG, Jinsong CHEN, Xiyuan QIAN. Calligraphy Character Skeleton Extraction Based on Improved Conditional Generative Adversarial Network [J]. Computer Engineering, 2023, 49(10): 272-279.

Please choose a citation manager

Content to export