K-Flix: Clustering-Based Video Streaming Traffic Identification in Programmable Data Planes

• Amaury Teixeira Cassola UFRGS
• Alberto Schaeffer-Filho UFRGS

DOI: https://doi.org/10.5753/sbrc.2025.5862

Resumo

Given the demand for video streaming on the Internet, specific Quality of Service (QoS) solutions become necessary, the implementation of which depends on the timely identification of such traffic. With this goal, this work uses Clustering for video traffic classification by offloading a Nearest Centroid Classifier to the data plane. A prototype of the proposed system was developed in a virtual environment and tests were executed using real traffic captures. Accuracies of over 98% were achieved on all tests, demonstrating the potential of the technique.

Palavras-chave: Traffic Classification, Programmable Data Planes, Machine Learning, Clustering, Video Streaming

Referências

Bosshart, P., Daly, D., Gibb, G., Izzard, M., McKeown, N., Rexford, J., Schlesinger, C., Talayco, D., Vahdat, A., Varghese, G., and Walker, D. (2014). P4: programming protocol-independent packet processors. SIGCOMM Comput. Commun. Rev., 44(3):87–95.

Bosshart, P., Gibb, G., Kim, H.-S., Varghese, G., McKeown, N., Izzard, M., Mujica, F., and Horowitz, M. (2013). Forwarding metamorphosis: fast programmable match-action processing in hardware for SDN. SIGCOMM Comput. Commun. Rev., 43(4):99–110.

Boutaba, R., Salahuddin, M., Limam, N., Ayoubi, S., Shahriar, N., Estrada-Solano, F., and Caicedo, M. (2018). A comprehensive survey on machine learning for networking: Evolution, applications and research opportunities. Journal of Internet Services and Applications, 9.

Cannarozzo, L., Morais, T. B., de Souza, P. S. S., Gobatto, L. R., Lamb, I. P., Duarte, P. A. P. R., Azambuja, J. R. F., Lorenzon, A. F., Rossi, F. D., Cordeiro, W., and Luizelli, M. C. (2024). Spinner: Enabling in-network flow clustering entirely in a programmable data plane. In NOMS 2024-2024 IEEE Network Operations and Management Symposium, pages 1–9.

Cassola, A. (2025). K-Flix Repository. [Online] Available: [link].

Coelho, B. and Schaeffer-Filho, A. (2022). Backorders: using random forests to detect DDoS attacks in programmable data planes. In Proceedings of the 5th International Workshop on P4 in Europe, EuroP4 ’22, pages 1–7, New York, NY, USA. Association for Computing Machinery.

Dalmazo, B. L., Marques, J. A., Costa, L. R., Bonfim, M. S., Carvalho, R. N., da Silva, A. S., Fernandes, S., Bordim, J. L., Alchieri, E., Schaeffer-Filho, A., Paschoal Gaspary, L., and Cordeiro, W. (2021). A systematic review on distributed denial of service attack defense mechanisms in programmable networks. International Journal of Network Management, 31(6):e2163.

Dias Knob, L. A., Esteves, R. P., Granville, L. Z., and Rockenbach Tarouco, L. M. (2017). Mitigating elephant flows in SDN-based IXP networks. In 2017 IEEE Symposium on Computers and Communications (ISCC), pages 1352–1359.

Dong, Y.-N., Zhao, J.-J., and Jin, J. (2017). Novel feature selection and classification of internet video traffic based on a hierarchical scheme. Comput. Netw., 119(C):102–111.

Friedman, R., Goaz, O., and Rottenstreich, O. (2021). Clustreams: Data plane clustering. In Proceedings of the ACM SIGCOMM Symposium on SDN Research (SOSR), SOSR ’21, pages 101–107, New York, NY, USA. Association for Computing Machinery.

Hauser, F., Haberle, M., Merling, D., Lindner, S., Gurevich, V., Zeiger, F., Frank, R., and Menth, M. (2023). A survey on data plane programming with P4: Fundamentals, advances, and applied research. Journal of Network and Computer Applications, 212:103561.

Nguyen, T. T. and Armitage, G. (2008). A survey of techniques for internet traffic classification using machine learning. IEEE Communications Surveys Tutorials, 10(4):56–76.

Nunes, D. C., Coelho, B. L., Parizotto, R., and Schaeffer-Filho, A. (2023). Serene: Handling the effects of stragglers in in-network machine learning aggregation. In NOMS 2023-2023 IEEE/IFIP Network Operations and Management Symposium, pages 1–10.

Parizotto, R., Coelho, B. L., Nunes, D. C., Haque, I., and Schaeffer-Filho, A. (2023). Offloading machine learning to programmable data planes: A systematic survey. ACM Comput. Surv., 56(1).

Sandvine, I. (2023). Global internet phenomena report 2023. [Online]. Available: [link].

Shamsimukhametov, D., Liubogoshchev, M., Khorov, E., and Akyildiz, I. F. (2021). Youtube, netflix, web dataset for encrypted traffic classification. [Online]. DOI: 10.21227/s7x7-wd58.

Song, F., Guo, Z., and Mei, D. (2010). Feature selection using principal component analysis. In 2010 International Conference on System Science, Engineering Design and Manufacturing Informatization, volume 1, pages 27–30.

Usama, M., Qadir, J., Raza, A., Arif, H., Yau, K.-L. A., Elkhatib, Y., Hussain, A., and Al-Fuqaha, A. (2019). Unsupervised machine learning for networking: Techniques, applications and research challenges. IEEE Access, 7:65579–65615.

Xavier, B. M., Silva Guimaraes, R., Comarela, G., and Martinello, M. (2022). Map4: A pragmatic framework for in-network machine learning traffic classification. IEEE Transactions on Network and Service Management, 19(4):4176–4188.

Xiong, Z. and Zilberman, N. (2019). Do switches dream of machine learning? Toward in-network classification. In Proceedings of the 18th ACM Workshop on Hot Topics in Networks, HotNets ’19, pages 25–33, New York, NY, USA. Association for Computing Machinery.

Zhang, J., Xiang, Y., Wang, Y., Zhou, W., Xiang, Y., and Guan, Y. (2013). Network traffic classification using correlation information. IEEE Transactions on Parallel and Distributed Systems, 24(1):104–117.

Zhang, Q. and Sun, S. (2010). A centroid k-nearest neighbor method. In Cao, L., Feng, Y., and Zhong, J., editors, Advanced Data Mining and Applications, pages 278–285, Berlin, Heidelberg. Springer Berlin Heidelberg.

Zhu, X. and Zhang, Y. (2022). Machine-learning-assisted traffic classification of user activities at programmable data plane. In 2022 23rd Asia-Pacific Network Operations and Management Symposium (APNOMS), pages 01–04.