Phân loại luồng dữ liệu dựa trên học chuyển giao đa nguồn trong hệ thống mạng SDN phân tán


  • Hoang Nam Thang Hanoi University of Civil Engineering
  • Nguyen Tran Le Tuan Hanoi University of Civil Engineering
  • Duong Cong Son Hanoi University of Civil Engineering
  • Tong Van Van Hanoi University of Science and Technology
  • Tran Hai Anh Hanoi University of Science and Technology



traffic classification, SDN, transfer learning, TrAdaBoost, multisource TrAdaBoost

Tóm tắt

Abstract—Network traffic classification (TC) is a critical task in network management, security and information security. As network encryption becomes more popular, TC-based machine learning methods have shown great performance, compared to other TC approaches such as port-based or payload inspection. Besides, recent studies on Software-defined networking (SDN) architecture have addressed the data consistency problem in distributed SDN. This means that the TC problem in distributed SDN with multiple domains can now be considered as one domain. Nevertheless, when a new SDN domain is added to the distributed system, the lack of network data on this domain is inevitable. This can make it difficult to train a good TC model for the new domain due to the absence of a training dataset. To address the problem of insufficient training data in a new SDN domain, this paper proposes a algorithm, called MMSTrAda (modified multiple source TrAdaBoost), a transfer learning method that utilizes knowledge already learned from exsisting SDN domains to improve the performance of the TC model in a new domain. Specifically, our proposal is based on a Multisource TradaBoost algorithm that takes advantage of useful data from various source domains. The experimental results show that the TC model in a new domain based on our proposal achieves about 88% macro-F1, when detecting three popular network services: E-commerce, Interactive data, and Video on-demand.


Download data is not yet available.


. J. Yan and J. Yuan, “A survey of traffic classification in software defined networks,” in 2018 1st IEEE International Conference on Hot Information-Centric Networking (HotICN). IEEE, 2018, pp. 200–206.

. M. Lotfollahi, M. Jafari Siavoshani, R. Shirali Hossein Zade, and M. Saberian, “Deep packet: A novel approach for encrypted traffic classification using deep learning,” Soft Computing, vol. 24, no. 3, pp. 1999–2012, 2020.

. K.-C. Chiu, C.-C. Liu, and L.-D. Chou, “Capc: Packet-based network service classifier with convolutional autoencoder,” IEEE Access, vol. 8, pp. 218 081–218 094, 2020.

. V. Tong, H. A. Tran, S. Souihi, and A. Mellouk, “A novel quic traffic classifier based on convolutional neural networks,” in 2018 IEEE Global Communications Conference (GLOBECOM). IEEE, 2018, pp. 1–6.

. P. Wang, F. Ye, X. Chen, and Y. Qian, “Datanet: Deep learning based encrypted network traffic classification in sdn home gateway,” IEEE Access, vol. 6, pp. 55 380–55 391, 2018.

. Tuan, T. A., Cuong, N. N., Anh, N. V., & Long, H. V. . (2023). Proposing the application of a deep learning model to detect the malicious IP address of botnet in the computer network. Journal of Science and Technology on Information Security, 3(17), 43-52.

. Quy, T. N., Tung, N. T., Trung, D. Q., & Viet, D. H. (2022). Convolutional neural network based sidechannel attacks. Journal of Science and Technology on Information Security, 1(15), 26-37.

. Dung, N. T., Quân, N. V., & Hùng, N. V. (2023). Application of deep learning model in network reconnaissance attack detection. Journal of Science and Technology on Information Security, 2(16), 60-72.

. D. Kreutz, F. M. Ramos, P. E. Verissimo, C. E. Rothenberg, S. Azodolmolky, and S. Uhlig, “Software-defined networking: A comprehensive survey,” Proceedings of the IEEE, vol. 103, no. 1, pp. 14–76, 2014.

. N.-T. Hoang, V. Tong, H. A. Tran, C. S. Duong, and T. L. T. Nguyen, “Lstm-based server and route selection in distributed and heterogeneous sdn network,” Journal of Computer Science and Cybernetics, vol. 39, no. 1, pp. 79– 99, 2023.

. T. Moufakir, M. F. Zhani, A. Gherbi, and O. Bouachir, “Collaborative multi-domain routing in sdn environments,” Journal of Network and Systems Management, vol. 30, pp. 1–23, 2022.

. F. Bannour, S. Souihi, and A. Mellouk, “Distributed sdn control: Survey, taxonomy, and challenges,” IEEE Communications Surveys & Tutorials, vol. 20, no. 1, pp. 333–354, 2017.

. N.-T. Hoang, H.-N. Nguyen, H.-A. Tran, and S. Souihi, “A novel adaptive east–west interface for a heterogeneous and distributed sdn network,” Electronics, vol. 11, no. 7, p. 975, 2022.

. Y. Yao and G. Doretto, “Boosting for transfer learning with multiple sources,” in 2010 IEEE computer society conference on computer vision and pattern recognition. IEEE, 2010, pp. 1855–1862.

. “Network traffic classification based on transfer learning,” Computers & Electrical Engineering, vol. 69, pp. 920–927, 2018.

. Z. Taghiyarrenani and H. Farsi, “Domain adaptation with maximum margin criterion with application to network traffic classification,” pp. 159–169, 2022.

. W. Dai, Q. Yang, G.-R. Xue, and Y. Yu, “Boosting for transfer learning,” in Proceedings of the 24th international conference on Machine learning, 2007, pp. 193–200.

. H. He, K. Khoshelham, and C. Fraser, “A multiclass tradaboost transfer learning algorithm for the classification of mobile lidar data,” ISPRS Journal of Photogrammetry and Remote Sensing, vol. 166, pp. 118–127, 2020.

. M. Grandini, E. Bagli, and G. Visani, “Metrics for multi-class classification: an overview,” arXiv preprint arXiv:2008.05756, 2020.


Abstract views: 108 / PDF downloads: 6



How to Cite

Thắng, H. N., Tuấn, N. T. L., Sơn, D. C., Vạn, T. V., & Anh, T. H. (2023). Phân loại luồng dữ liệu dựa trên học chuyển giao đa nguồn trong hệ thống mạng SDN phân tán. Journal of Science and Technology on Information Security, 2(19), 59-60.