Applying Big Data, Machine Learning, and SDN/NFV for 5G Early-Stage Traffic Classification and Network QoS Control
Keywords:Traffic classification, Machine Learning, Big Data, SON, 5G, InfoSphere, Streaming
Due to the rapid growth of mobile broadband and IoT applications, the early-stage mobile traffic classification becomes more important for traffic engineering to guarantee Quality of Service (QoS), implement resource management, and network security. Therefore, identifying traffic flows based on a few packets during the early state has attracted attention in both academic and industrial fields. However, a powerful and flexible platform to handle millions of traffic flows is still challenging. This study aims to demonstrate how to integrate various state-of-the-art machine learning (ML) algorithms, big data analytics platforms, software-defined networking (SDN), and network functions virtualization (NFV) to build a comprehensive framework for developing future 5G SON applications. This platform successfully collected, stored, analyzed, and identified a huge number of real-time traffic flows at broadband Mobile Lab (BML), National Chiao Tung University (NCTU). Moreover, we also implemented network QoS control to configure priorities per-flow traffic to enable bandwidth guarantees for each application by using SDN. Finally, the performance of the proposed models was evaluated by applying them to a real testbed environment. The powerful computing capacity of the platform was also analyzed.
(1) Y. J. Chen, L. C. Wang, F. Y. Lin, and B. S. Lin, “Deterministic Quality of Service Guarantee for Dynamic Service Chaining in Software Defined Networking,” IEEE Trans. Netw. Serv. Manag., vol. 14, no. 4, pp. 991–1002, 2017.
(2) I. C. Hsieh, L. P. Tung, and B. S. P. Lin, “On the classification of mobile broadband applications,” IEEE Int. Work. Comput. Aided Model. Des. Commun. Links Networks, CAMAD, pp. 128–134, 2016.
(3) J. Zhang, C. Chen, Y. Xiang, W. Zhou, and Y. Xiang, “Internet traffic
classification by aggregating correlated naive bayes predictions,” IEEE Trans. Inf. Forensics Secur., vol. 8, no. 1, pp. 5–15, 2013.
(4) W. Ke, Y. Wang, X. Lei, and B. Wei, “Spark-Based Feature Selection Algorithm of Network Traffic Classification,” 2017 13th Int. Conf. Comput. Intell. Secur., pp. 140–144, 2017.
(5) N. F. Huang, G. Y. Jai, H. C. Chao, Y. J. Tzang, and H. Y. Chang, “Application traffic classification at the early stage by characterizing application rounds,” Inf. Sci. (Ny)., vol. 232, no. 22, pp. 130–142, 2013.
(6) L. Peng, B. Yang, Y. Chen, and T. Wu, “How many packets are most effective for early stage traffic identification: An experimental study,” China Commun., vol. 11, no. 9, pp. 183–193, 2014.
(7) G. Aceto, D. Ciuonzo, G. Aceto, D. Ciuonzo, A. Montieri, and A. Pescapé, “Traffic Classification of Mobile Apps through Traffic Classification of Mobile Apps through,” no. September, pp. 2–7, 2017.
(8) R. Alshammari and A. N. Zincir-Heywood, “Identification of VoIP encrypted traffic using a machine learning approach,” J. King Saud Univ. - Comput. Inf. Sci., vol. 27, no. 1, pp. 77–92, 2015.
(9) M. Shafiq, X. Yu, and D. Wang, “Robust Feature Selection for IM Applications at Early Stage Traffic Classification Using Machine Learning Algorithms,” 2017 IEEE 19th Int. Conf. High Perform. Comput. Commun. IEEE 15th Int. Conf. Smart City; IEEE 3rd Int. Conf. Data Sci. Syst., pp.
(10) B. Hullár, S. Laki, and A. György, “Efficient methods for early protocol identification,” IEEE J. Sel. Areas Commun., vol. 32, no. 10, pp. 1907–1918, 2014.
(11) B. P. Lin, F. J. Lin, and L. Tung, “The Roles of 5G Mobile Broadband in the Development of IoT, Big Data, Cloud and SDN,” Commun. Netw., vol. 8, no, no. February, pp. 9–21, 2016.
(12) B. P. Lin, L. Tung, F. Tseng, I. Hsieh, Y. Wang, and S. Chou, “Performance Estimation of MAR for Outdoor Navigation Applications based on 5G Mobile Broadband by using Smart Mobile Devices.”
(13) B. S. P. Lin, W. H. Tsai, C. C. Wu, P. H. Hsu, J. Y. Huang, and T. H. Liu, “The design of cloud-based 4G/LTE for mobile augmented reality with smart mobile devices,” Proc. - 2013 IEEE 7th Int. Symp. Serv. Syst. Eng. SOSE 2013, pp. 561–566, 2013.
(14) D. Sinh, L. Le, L. Tung, and B. P. Lin, “The Challenges of Applying SDN / NFV for 5G & IoT,” in The 14th IEEE - VTS: Asia Pacific Wireless Communications Symposium (APWCS), Incheon, Korea, August 2017.
(15) Le Luong Vy; Li-Ping Tung; Bao-Shuh Paul Lin, “Big data and machine learning driven handover management and forecasting,” in IEEE Standards for Communications and Networking (CSCN), 2017 IEEE Conference on, 2017, pp. 214–219.
(16) L. Le, D. Sinh, L. Tung, and B. P. Lin, “A Practical Model for Traffic Forecasting based on Big Data , Machine-learning , and Network KPIs,” pp. 3–6, 2018.
(17) M. Conti, L. V. Mancini, R. Spolaor, and N. V. Verde, “Analyzing Android Encrypted Network Traffic to Identify User Actions,” IEEE Trans. Inf. Forensics Secur., vol. 11, no. 1, pp. 114–125, 2016.
(18) B. S. Lin et al., “The design of big data analytics for testing & measurement and traffic flow on an experimental 4G/LTE network,” 2015 24th Wirel. Opt. Commun. Conf. WOCC 2015, pp. 40–44, 2015.
(19) D. L. C. Dutra, M. Bagaa, T. Taleb, and K. Samdanis, “Ensuring End-
to-End QoS Based on Multi-Paths Routing Using SDN Technology,” GLOBECOM 2017 - 2017 IEEE Glob. Commun. Conf., pp. 1–6, 2017.
(20) H. Krishna, N. L. M. Van Adrichem, and F. A. Kuipers, “Providing bandwidth guarantees with OpenFlow,” 2016 IEEE Symp. Commun. Veh. Technol. Benelux, SCVT 2016, pp. 0–5, 2016.