eISSN: 3087-4068 editor@aimjournals.com
All Journals
Submit your article

International Research Journal of Advanced Engineering and Technology

Open Access Peer Review International
Open Access

A Novel Adversarial Framework for Urban Traffic Congestion Analysis: A Supply-Demand Perspective

DOI
PDF
Dr. Julian R. Everleigh 1 , Prof. Elena M. Petrova 1 ,
4 Department of Transportation Engineering, Urban Dynamics Research Group, University of Copenhagen, Denmark
4 Faculty of Data Science, V.O. Smirnov Institute of Computational Sciences, St. Petersburg, Russia

Abstract

Introduction: Urban traffic congestion poses a significant challenge to modern transportation systems. While deep learning models, particularly Graph Neural Networks (GNNs), have shown promise in traffic forecasting, they often focus on predicting future states based on historical patterns. This approach fails to provide a comprehensive understanding of network vulnerabilities when faced with sudden, unexpected disruptions, such as a traffic accident.

Methods: We propose a novel, adversarially-inspired framework called ATraffic to analyze urban traffic congestion. Drawing an analogy from Word Sense Disambiguation (WSD), which resolves ambiguity by analyzing context, our framework utilizes a "traffic attacker" to simulate a targeted, localized disruption to the network's capacity. This attacker reduces the "supply" of a specific road segment, allowing us to observe how the ensuing congestion propagates and impacts the overall "supply-demand" balance. Our model integrates a spatio-temporal GNN architecture to capture the dynamic dependencies of the road network, while the adversarial module systematically identifies and "attacks" critical nodes.

Results: Our experiments demonstrate that the proposed framework can effectively simulate the ripple effects of a localized disruption. We show that a minor, simulated attack can lead to a significant increase in total network travel time and can identify specific, vulnerable network segments where the supply-demand balance is most critically affected. The model's predictions align with established principles of congestion propagation, highlighting its utility as an analytical tool for urban planners.

Discussion: This research presents a new paradigm for studying traffic congestion by treating it as a dynamic response to a deliberate shock on the network's supply side. Our findings confirm that understanding and mitigating congestion requires not only predictive capabilities but also an understanding of system resilience. The "traffic attacker" framework offers a valuable tool for stress-testing road networks, revealing hidden bottlenecks and guiding strategic infrastructure improvements.

Conclusion: The adversarial, supply-shock approach provides a robust method for analyzing urban traffic congestion. By simulating disruptions, we can gain deeper insights into the complex dynamics of traffic flow and develop more resilient and sustainable transportation systems.

Keywords

Traffic Congestion, Traffic Forecasting, Graph Neural Networks

References

📄 Li, Y., Yu, R., Shahabi, C., & Liu, Y. (2017). Diffusion Convolutional Recurrent Neural Network: Data‐Driven Traffic Forecasting. arXiv preprint arXiv:1707.01926.
📄 Yu, B., Yin, H., & Zhu, Z. (2017). Spatio‐Temporal Graph Convolutional Networks: A Deep Learning Framework for Traffic Forecasting. arXiv preprint arXiv:1709.04875.
📄 Chen, C., Li, K., Teo, S. G., et al. (2019). Gated Residual Recurrent Graph Neural Networks for Traffic Prediction. Proceedings of the AAAI Conference on Artificial Intelligence, 33(1), 485–492. https://doi.org/10.1609/aaai.v33i01.3301485
📄 Song, C., Lin, Y., Guo, S., & Wan, H. (2020). Spatial‐Temporal Synchronous Graph Convolutional Networks: A New Framework for Spatial‐Temporal Network Data Forecasting. Proceedings of the AAAI Conference on Artificial Intelligence, 34(1), 914–921. https://doi.org/10.1609/aaai.v34i01.5438
📄 Lee, H., Jin, S., Chu, H., Lim, H., & Ko, S. (2021). Learning to Remember Patterns: Pattern Matching Memory Networks for Traffic Forecasting. arXiv preprint arXiv:2110.10380.
📄 Guo, K., Hu, Y., Sun, Y., Qian, S., Gao, J., & Yin, B. (2021). Hierarchical Graph Convolution Network for Traffic Forecasting. Proceedings of the AAAI Conference on Artificial Intelligence, 35(1), 151–159. https://doi.org/10.1609/aaai.v35i1.16088
📄 Fang, Z., Pan, L., Chen, L., Du, Y., & Gao, Y. (2021). MDTP: A Multi‐Source Deep Traffic Prediction Framework Over Spatio‐Temporal Trajectory Data. Proceedings of the VLDB Endowment, 14(8), 1289–1297. https://doi.org/10.14778/3457390.3457394
📄 Oreshkin, B. N., Amini, A., Coyle, L., & Coates, M. (2021). FC‐GAGA: Fully Connected Gated Graph Architecture for Spatio‐Temporal Traffic Forecasting. Proceedings of the AAAI Conference on Artificial Intelligence, 35(10), 9233–9241. https://doi.org/10.1609/aaai.v35i10.17114
📄 Cirstea, R.‐G., Yang, B., Guo, C., Kieu, T., & Pan, S. (2022). Towards Spatio‐Temporal Aware Traffic Time Series Forecasting. In 2022 IEEE 38th International Conference on Data Engineering (ICDE) (pp. 2900–2913). IEEE.
📄 Li, M., & Zhu, Z. (2021). Spatial‐Temporal Fusion Graph Neural Networks for Traffic Flow Forecasting. Proceedings of the AAAI Conference on Artificial Intelligence, 35(5), 4189–4196. https://doi.org/10.1609/aaai.v35i5.16542
📄 Chen, Y., Segovia, I., & Gel, Y. R. (2021). Z‐GCNETs: Time Zigzags at Graph Convolutional Networks for Time Series Forecasting. In International Conference on Machine Learning (PMLR) (pp. 1684–1694).
📄 Wu, Z., Pan, S., Long, G., Jiang, J., & Zhang, C. (2019). Graph WaveNet for Deep Spatial‐Temporal Graph Modeling. arXiv preprint arXiv:1906.00121(2019), 1907–1913. https://doi.org/10.24963/ijcai.2019/264
📄 Guo, S., Lin, Y., Feng, N., Song, C., & Wan, H. (2019). Attention Based Spatial‐Temporal Graph Convolutional Networks for Traffic Flow Forecasting. Proceedings of the AAAI Conference on Artificial Intelligence, 33(1), 922–929. https://doi.org/10.1609/aaai.v33i01.3301922
📄 Bai, L., Yao, L., Li, C., Wang, X., & Wang, C. (2020). Adaptive Graph Convolutional Recurrent Network for Traffic Forecasting. arXiv preprint arXiv:2007.02842.
📄 Zheng, C., Fan, X., Wang, C., & Qi, J. (2020). GMAN: A Graph Multi‐Attention Network for Traffic Prediction. Proceedings of the AAAI Conference on Artificial Intelligence, 34(1), 1234–1241. https://doi.org/10.1609/aaai.v34i01.5477
📄 Han, L., Du, B., Sun, L., Fu, Y., Lv, Y., & Xiong, H. (2021). Dynamic and Multi‐Faceted Spatio‐Temporal Deep Learning for Traffic Speed Forecasting. Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining (2021), 547–555. https://doi.org/10.1145/3447548.3467275
📄 Fang, Z., Long, Q., Song, G., & Xie, K. (2021). Spatial‐Temporal Graph Ode Networks for Traffic Flow Forecasting. Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining (2021), 364–373. https://doi.org/10.1145/3447548.3467430
📄 Choi, J., Choi, H., Hwang, J., & Park, N. (2022). Graph Neural Controlled Differential Equations for Traffic Forecasting. Proceedings of the AAAI Conference on Artificial Intelligence, 36(6), 6367–6374. https://doi.org/10.1609/aaai.v36i6.20587
📄 Ji, J., Wang, J., Jiang, Z., Jiang, J., & Zhang, H. (2022). STDEN: Towards Physics‐Guided Neural Networks for Traffic Flow Prediction. Proceedings of the AAAI Conference on Artificial Intelligence, 36(4), 4048–4056. https://doi.org/10.1609/aaai.v36i4.20322
📄 Wang, J., & Sun, J. (2019). Research on Traffic Congestion of Urban Main Road Under Accident Conditions. https://api.semanticscholar.org/CorpusID:203584582.
📄 Zheng, Z., Wang, Z., Zhu, L., & Jiang, H. (2020). Determinants of the Congestion Caused by a Traffic Accident in Urban Road Networks. Accident Analysis & Prevention, 136, 105327. https://doi.org/10.1016/j.aap.2019.105327
📄 Long, J., Gao, Z., Ren, H., & Lian, A. (2008). Urban Traffic Congestion Propagation and Bottleneck Identification. Science in China - Series F: Information Sciences, 51(7), 948–964. https://doi.org/10.1007/s11432‐008‐0038‐9
📄 Hale, D., Jagannathan, R., Xyntarakis, M., et al. (2016). Traffic Bottlenecks: Identification and Solutions (Tech. rep.). Federal Highway Administration, Office of Operations Research.
📄 Mirshahi, M., Obenberger, J., Fuhs, C. A., et al. (2007). Active Traffic Management: The next Step in Congestion Management (Tech. rep.). Federal Highway Administration.
📄 Chanussot, L., Das, A., Goyal, S., et al. (2021). Open Catalyst 2020 (OC20) Dataset and Community Challenges. ACS Catalysis, 11(10), 6059–6072. https://doi.org/10.1021/acscatal.0c04525
📄 Bando, M., Hasebe, K., Nakayama, A., Shibata, A., & Sugiyama, Y. (1995). Dynamical Model of Traffic Congestion and Numerical Simulation. Physical Review E, 51(2), 1035–1042. https://doi.org/10.1103/physreve.51.1035
📄 Arnott, R., Rave, T., & Schöb, R. (2005). Alleviating Urban Traffic Congestion. MIT Press Books, 1.
📄 Pattara‐Atikom, W., Pongpaibool, P., & Thajchayapong, S. (2006). Estimating Road Traffic Congestion Using Vehicle Velocity. In 2006 6th International Conference on ITS Telecommunications (IEEE) (pp. 1001–1004).
📄 Jia, S., Peng, H., & Liu, S. (2011). Urban Traffic State Estimation Considering Resident Travel Characteristics and Road Network Capacity. Journal of Transportation Systems Engineering and Information Technology, 11(5), 81–85. https://doi.org/10.1016/s1570‐6672(10)60142‐0
📄 He, F., Yan, X., Liu, Y., & Ma, L. (2016). A Traffic Congestion Assessment Method for Urban Road Networks Based on Speed Performance Index. Procedia Engineering, 137, 425–433. https://doi.org/10.1016/j.proeng.2016.01.277
📄 Quiroga, C. A. (2000). Performance Measures and Data Requirements for Congestion Management Systems. Transportation Research Part C: Emerging Technologies, 8(1/6), 287–306. https://doi.org/10.1016/s0968‐090x(00)00008‐5
📄 Levinson, H. S., & Lomax, T. J. (1996). Developing a Travel Time Congestion Index. Transportation Research Record Journal of the Transportation Research Board, 1564(1), 1–10. https://doi.org/10.1177/0361198196156400101
📄 Afrin, T., & Yodo, N. (2020). A Survey of Road Traffic Congestion Measures Towards a Sustainable and Resilient Transportation System. Sustainability, 12(11), 4660. https://doi.org/10.3390/su12114660
📄 Yao, H., Tang, X., Wei, H., Zheng, G., & Li, Z. (2019). Revisiting Spatial‐Temporal Similarity: A Deep Learning Framework for Traffic Prediction. Proceedings of the AAAI Conference on Artificial Intelligence, 33(1), 5668–5675. https://doi.org/10.1609/aaai.v33i01.33015668
📄 Diao, Z., Wang, X., Zhang, D., Liu, Y., Xie, K., & He, S. (2019). Dynamic Spatial‐Temporal Graph Convolutional Neural Networks for Traffic Forecasting. Proceedings of the AAAI Conference on Artificial Intelligence, 33(1), 890–897. https://doi.org/10.1609/aaai.v33i01.3301890
📄 Akbarzadeh, M., Memarmontazerin, S., Derrible, S., & SalehiReihani, S. F. (2019). The Role of Travel Demand and Network Centrality on the Connectivity and Resilience of an Urban Street System. Transportation, 46(4), 1127–1141. https://doi.org/10.1007/s11116‐017‐9814‐y
📄 Wu, C., Pei, Y., & Gao, J. (2015). Model for Estimation Urban Transportation Supply‐Demand Ratio. Mathematical Problems in Engineering, 2015(1), 502739. https://doi.org/10.1155/2015/502739
📄 Wang, T., Yang, B., Chen, C., & Guan, X. (2019). Wireless Charging Lane Deployment in Urban Areas Considering Traffic Light and Regional Energy Supply‐Demand Balance. In 2019 IEEE 89th Vehicular Technology Conference (VTC2019‐Spring) (pp. 1–5). IEEE.
📄 Guo, X., Yu, Z., Wang, P., et al. (2021). Urban Traffic Light Control via Active Multi‐Agent Communication and Supply‐Demand Modeling. IEEE Transactions on Knowledge and Data Engineering, 35(4), 4346–4356. https://doi.org/10.1109/tkde.2021.3130258
📄 Nazzal, M., Khreishah, A., Lee, J., Angizi, S., Al‐Fuqaha, A., & Guizani, M. (2024). Semi‐Decentralized Inference in Heterogeneous Graph Neural Networks for Traffic Demand Forecasting: An Edge‐Computing Approach. IEEE Transactions on Vehicular Technology, 73(12), 19400–19416. https://doi.org/10.1109/tvt.2024.3355971
📄 Zügner, D., Akbarnejad, A., & Günnemann, S. (2018). Adversarial Attacks on Neural Networks for Graph Data. Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining (2018), 2847–2856. https://doi.org/10.1145/3219819.3220078
📄 Dai, H., Li, H., Tian, T., et al. (2018). Adversarial Attack on Graph Structured Data. In International Conference on Machine Learning (PMLR) (pp. 1115–1124).
📄 Sun, Y., Wang, S., Tang, X., Hsieh, T. Y., & Honavar, V. (2020). Adversarial Attacks on Graph Neural Networks via Node Injections: A Hierarchical Reinforcement Learning Approach. Proceedings of The Web Conference 2020 (2020), 673–683. https://doi.org/10.1145/3366423.3380149
📄 Liu, W., Wen, Y., Yu, Z., & Yang, M. (2016). Large‐Margin Softmax Loss for Convolutional Neural Networks. arXiv preprint arXiv:1612.02295.
📄 Ying, C., Cai, T., Luo, S., et al. (2021). Do Transformers Really Perform Bad for Graph Representation?. arXiv preprint arXiv:2106.05234.
📄 Zuo, Y., Liu, G., Lin, H., Guo, J., Hu, X., & Wu, J. (2018). Embedding Temporal Network via Neighborhood Formation. In Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining (pp. 2857–2866).
📄 Liang, C., Huang, Z., Liu, Y., et al. (2022). CBLab: Scalable Traffic Simulation With Enriched Data Supporting. arXiv preprint arXiv:2210.00896.
📄 Kipf, T. N., & Welling, M. (2016). Semi‐Supervised Classification With Graph Convolutional Networks. arXiv preprint arXiv:1609.02907.
📄 Dai, H., Dai, B., & Song, L. (2016). Discriminative Embeddings of Latent Variable Models for Structured Data. In International Conference on Machine Learning (PMLR) (pp. 2702–2711).
📄 Murchland, J. D. (1970). Braess’s Paradox of Traffic Flow. Transportation Research, 4(4), 391–394. https://doi.org/10.1016/0041‐1647(70)90196‐6
📄 Velickovic, P., Cucurull, G., Casanova, A., Romero, A., Lio, P., & Bengio, Y. (2017). Graph Attention Networks. Stat 1050, 20.
📄 Vaswani, A., Shazeer, N., Parmar, N., et al. (2017). Attention Is all You Need. arXiv.

Most read articles by the same author(s)