With the rise of living standards, more and more people choose to travel by car, which increases the pressure on the urban traffic network (TN). The TN needs to be re planned and designed. The main goal of the design, organization and management of the TN is to improve the service level and access to the TN. During the planning process, a reasonable and scientific TN model should be developed according to the characteristics of traffic operation in different regions. Therefore, this paper studies and designs the bilevel programming model of discrete TN based on the hybrid algorithm of machine learning and optimization. This paper first describes the construction of the bilevel programming model and the network structure, then designs the hybrid algorithm and sets the weight coefficient, and finally analyzes the sensitivity of the comparison of the average load degree of the road section and the time budget.

Jiaqing Li. Bilevel Programming Model of Discrete Traffic Network Based on Machine Learning Optimization Hybrid Algorithm. Machine Learning Theory and Practice (2022), Vol. 3, Issue 1: 35-43. https://doi.org/10.38007/ML.2022.030105.

[1] Ons Aouedi, Kandaraj Piamrat, Salima Hamma, Menuka Perera Jayasuriya Kuranage: Network traffic analysis using machine learning: an unsupervised approach to understand and slice your network. Ann. des Telecommunications 77(5-6): 297-309(2022). https://doi.org/10.1007/s12243-021-00889-1

[2] Lucas C. B. Guimaraes, Gabriel Antonio F. Rebello, Gustavo Franco Camilo, Lucas Airam C. de Souza, Otto Carlos M. B. Duarte: A threat monitoring system for intelligent data analytics of network traffic. Ann. Des Telecommunications 77(7-8): 539-554 (2022). https://doi.org/10.1007/s12243-021-00893-5

[3] Khac-Hoai Nam Bui, jiho Cho, Hongsuk Yi: Spatial-temporal graph neural network for traffic forecasting: An overview and open research issues. Appl. Intell. 52(3): 2763-2774 (2022). https://doi.org/10.1007/s10489-021-02587-w

[4] Muhammad U. llyas, Soltan Abed Alharbi: Machine learning approaches to network intrusion detection for contemporary internet traffic. Computing 104(5): 1061-1076 (2022). https://doi.org/10.1007/s00607-021-01050-5

[5] Kwihoon Kim, Joo-Hyung Lee, Hyun-Kyo Lim, Se Won Oh, Youn-Hee Han: Deep RNN-based network traffic classification scheme in edge computing system. Comput. Sci. Inf. Syst. 19(1): 165-184 (2022). https://doi.org/10.2298/CSIS200424038K

[6] Juma Ibrahim, Slavko Gajin: Entropy-based network traffic anomaly classification method resilient to deception. Comput. Sci. Inf. Syst. 19(1): 87-116 (2022). https://doi.org/10.2298/CSIS201229045I

[7] M. Govindarajan, V. Chandrasekaran, S. Anitha: Network Traffic Prediction Using Radial Kernelized-Tversky Indexes-Based Multilayer Classifier. Comput. Syst. Sci. Eng.40(3): 851-863 (2022). https://doi.org/10.32604/csse.2022.019298

[8] Vasaki Ponnusamy, Aun Yichiet, N. Z. Jhanjhi, Mamoona Humayun, Maram Fahhad Almufareh: loT Wireless Intrusion Detection and Network Traffic Analysis. Comput. Syst. Sci. Eng. 40(3): 865-879 (2022). https://doi.org/10.32604/csse.2022.018801

[9] Dhaya Ramakrishnan, Kanthavel Radhakrishnan: Applying deep convolutional neural network (DCNN) algorithm in the cloud autonomous vehicles traffic model. Int. Arab J. Inf. Technol. 19(2): 186-194 (2022). https://doi.org/10.34028/iajit/19/2/5

[10] Amir Alidadi, Saeedreza Arab, Tayebeh Askari: A novel optimized routing algorithm for QoS traffic engineering in SDN-based mobile networks. ICT Express 8(1): 130-134 (2022). https://doi.org/10.1016/j.icte.2021.12.010

[11] Deepika Saxena, Ashutosh Kumar Singh: An Intelligent Traffic Entropy Learning-Based Load Management Model for Cloud Networks. IEEE Netw. Lett. 4(2): 59-63 (2022). https://doi.org/10.1109/LNET.2022.3156055

[12] Rakesh Kumar, Mayank Swarnkar, Gaurav Singal, Neeraj Kumar D: loT Network Traffic Classification Using Machine Learning Algorithms: An Experimental Analysis. IEEE Internet Things J. 9(2): 989-1008 (2022). https://doi.org/10.1109/JIOT.2021.3121517

[13] Dandy Pramana Hostiadi, Tohari Ahmad: Hybrid model for bot group activity detection using similarity and correlation approaches based on network traffic flows analysis. J. King Saud Univ. Comput. Inf. Sci. 34(7): 4219-4232 (2022). https://doi.org/10.1016/j.jksuci.2022.05.004

[14] Pallaviram Sure, Chithra Priya Srinivasan, C. Narendra Babu : Spatio-Temporal Constraint-Based Low Rank Matrix Completion Approaches for Road TNs. IEEE Trans. Intell. Transp. Syst. 23(8): 13452-13462 (2022). https://doi.org/10.1109/TITS.2021.3124613

[15] Jinoh Kim, Makiya Nakashima, Wenjun Fan, Simeon Wuthier, Xiaobo Zhou, lkkyun Kim, Sang-Yoon Chang: A Machine Learning Approach to Anomaly Detection Based on Traffic Monitoring for Secure Blockchain Networking. IEEE Trans. Netw. Serv. Manag.19 (3): 3619-3632 (2022). https://doi.org/10.1109/TNSM.2022.3173598

[16] Alessio Sacco, Flavio Esposito, Guido Marchetto: Restoring Application Traffic of Latency-Sensitive Networked Systems Using Adversarial Autoencoders. IEEE Trans. Netw. Serv. Manag. 19(3): 2521-2535 (2022). https://doi.org/10.1109/TNSM.2022.3192305

[17] Alessio Sacco, Flavio Esposito, Guido Marchetto: Restoring Application Traffic of Latency-Sensitive Networked Systems Using Adversarial Autoencoders. IEEE Trans. Netw. Serv. Manag. 19(3): 2521-2535 (2022). https://doi.org/10.1109/TNSM.2022.3192305

[18] Akbar Telikani, Amir H. Gandomi, Kim-Kwang Raymond Choo, Jun Shen o: A Cost-Sensitive Deep Learning-Based Approach for Network Traffic Classification. IEEE Trans. Netw. Serv. Manag. 19(1): 661-670 (2022). https://doi.org/10.1109/TNSM.2021.3112283