End-to-end heterogeneous graph neural networks for traffic assignment

被引:28
作者
Liu, Tong [1 ]
Meidani, Hadi [1 ]
机构
[1] Univ Illinois, Dept Civil & Environm Engn, Champaign, IL 61801 USA
基金
美国国家科学基金会;
关键词
Traffic assignment problem; Graph neural network; Traffic flow prediction; Flow conservation; Heterogeneity; ALGORITHM;
D O I
10.1016/j.trc.2024.104695
中图分类号
U [交通运输];
学科分类号
08 ; 0823 ;
摘要
The traffic assignment problem is one of the significant components of traffic flow analysis for which various solution approaches have been proposed. However, deploying these approaches for large-scale networks poses significant challenges. In this paper, we leverage the power of heterogeneous graph neural networks to propose a novel end-to-end surrogate model for traffic assignment, specifically user equilibrium traffic assignment problems. Our model integrates an adaptive graph attention mechanism with auxiliary "virtual"links connecting origin-destination node pairs, This integration enables the model to capture spatial traffic patterns across different links, By incorporating the node-based flow conservation law into the overall loss function, the model ensures the prediction results in compliance with flow conservation principles, resulting in highly accurate predictions for both link flow and flow-capacity ratios. We present numerical experiments on urban transportation networks and show that the proposed heterogeneous graph neural network model outperforms other conventional neural network models in terms of convergence rate and prediction accuracy. Notably, by introducing two different training strategies, the proposed heterogeneous graph neural network model can also be generalized to different network topologies. This approach offers a promising solution for complex traffic flow analysis and prediction, enhancing our understanding and management of a wide range of transportation systems.
引用
收藏
页数:14
相关论文
共 50 条
[31]   Investigation of an end-to-end neural architecture for image-based source term estimation [J].
Abdulaziz, A. ;
Altmann, Y. ;
McLaughlin, S. ;
Davies, M. E. .
2023 SENSOR SIGNAL PROCESSING FOR DEFENCE CONFERENCE, SSPD, 2023, :71-75
[32]   Automatic CWE Assignment for Vulnerabilities with Graph Neural Networks [J].
Liu, Peng ;
Ye, Wenzhe ;
Duan, Haiying ;
Li, Xianxian ;
Zhang, Shuyi ;
Li, Yongnan .
2023 3RD ASIA-PACIFIC CONFERENCE ON COMMUNICATIONS TECHNOLOGY AND COMPUTER SCIENCE, ACCTCS, 2023, :188-193
[33]   End-to-End Sleep Apnea Detection Using Single-Lead ECG Signal and 1-D Residual Neural Networks [J].
Sharan, Roneel V. ;
Berkovsky, Shlomo ;
Xiong, Hao ;
Coiera, Enrico .
JOURNAL OF MEDICAL AND BIOLOGICAL ENGINEERING, 2021, 41 (05) :758-766
[34]   MTGNet: Multi-Agent End-to-End Motion Trajectory Prediction with Multimodal Panoramic Dynamic Graph [J].
Dai, Yinfei ;
Zhang, Yuantong ;
Zhou, Xiuzhen ;
Wang, Qi ;
Song, Xiao ;
Wang, Shaoqiang .
APPLIED SCIENCES-BASEL, 2025, 15 (10)
[35]   End-to-End control of USV swarm using graph centric Multi-agent Reinforcement Learning [J].
Lee, Kanghoon ;
Ahn, Kyuree ;
Park, Jinkyoo .
2021 21ST INTERNATIONAL CONFERENCE ON CONTROL, AUTOMATION AND SYSTEMS (ICCAS 2021), 2021, :925-929
[36]   Predicting spatio-temporal traffic flow: a comprehensive end-to-end approach from surveillance cameras [J].
Feng, Yuxiang ;
Zhao, Yifan ;
Zhang, Xingchen ;
Batista, Sergio F. A. ;
Demiris, Yiannis ;
Angeloudis, Panagiotis .
TRANSPORTMETRICA B-TRANSPORT DYNAMICS, 2024, 12 (01)
[37]   Green Traffic Off-Loading Over Uncertain Shared Spectrums With End-to-End QoS Guarantee [J].
Li, Xuanheng ;
Xiao, Ruyi ;
Pan, Miao ;
Jiang, Fan ;
Zhao, Nan ;
Wang, Xianbin .
IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY, 2020, 69 (09) :9921-9937
[38]   Algorithm of End-to-End Integrated Quality Management [J].
Filippov, Aleksandr A. ;
Antonova, Anastasia A. ;
Antonova, Irina I. ;
Baranova, Irina A. ;
Nazarenko, Maxim A. .
2018 IEEE INTERNATIONAL CONFERENCE QUALITY MANAGEMENT, TRANSPORT AND INFORMATION SECURITY, INFORMATION TECHNOLOGIES (IT&QM&IS), 2018, :44-46
[39]   End-to-end Differentiable Clustering with Associative Memories [J].
Saha, Bishwajit ;
Krotov, Dmitry ;
Zaki, Mohammed J. ;
Ram, Parikshit .
INTERNATIONAL CONFERENCE ON MACHINE LEARNING, VOL 202, 2023, 202
[40]   Graph Convolutional Neural Networks with Traffic Turning Rules for Traffic Prediction of Urban Road Network [J].
Ding, Yan ;
Ma, Yaohong ;
Wang, Jiale ;
Li, Yunhao ;
Chen, Biyu .
Journal of Geo-Information Science, 2025, 27 (03) :653-667