Просмотр статьи


Номер журнала: 2021.1

Заголовок статьи: Анализ перспективных подходов и исследований по классификации потоков трафика для поддержания QoS методами ML в SDN-сетях

Резюме

Одной из важнейших задач, существующих в современных сетях, является поддержка качества обслуживания QoS на соответствующем уровне, что может быть достигнуто путем применения различных механизмов управления трафиком. Но для того, чтобы поддерживать параметры QoS в надлежащем состоянии, требуется знать типы трафика, проходящие по сети. С учетом высокотехнологичных и производительных сетей, таких как SDN-сети, классификация трафика обычными способами становится практически невозможной. На помощь приходят методы интеллектуального анализа данных, в т.ч. методы машинного обучения. В статье анализируются основные перспективные подходы к классификации трафика в режиме реального времени для поддержания QoS в SDN-сетях методами ML, а также представлен сравнительный обзор наиболее выдающихся работ.

Авторы

В. Ю. Деарт, В. А. Маньков, И. А. Краснова

Библиография

1. Гетьман А. И., Маркин Ю. В., Евстропов Е. Ф., Обыденков Д. О. Обзор задач и методов их решения в области классификации сетевого трафика // Труды ИСП РАН. 2017. Т. 29,
В. 3. С. 117–150. DOI: 10.15514/ISPRAS-2017-29(3)-8.
2. Boutaba R., Salahuddin M. A., Limam N., Ayoubi S., Shahriar N., Solano F. E., Rendon O. M.
A comprehensive survey on machine learning for networking: evolution, applications and re-search opportunities // Journal of Internet Services and Applications. 2018. № 9. P. 1–99. https://doi.org/10.1186/s13174-018-0087-2.
3. Harkut Dr Dinesh. An Overview of Network Traffic Classification Methods. 2015.
4. Шелухин О. И., Ерохин С. Д., Ванюшина А. В. Классификация IP-трафика методами ма-шинного обучения / под ред. О. И. Шелухина. М.: Горячая линия – Телеком, 2018. 282 с.
5. Xie J. et al. A Survey of Machine Learning Techniques Applied to Software Defined Network-ing (SDN): Research Issues and Challenges // IEEE Communications Surveys & Tutorials. 2018.
P. 393–430. https://doi.org/10.1109/comst.2018.2866942.
6. Zhao Y., Li Y., Zhang X., Geng G., Zhang W. and Sun Y. A Survey of Networking Applications Applying the Software Defined Networking Concept Based on Machine Learning // IEEE Ac-cess. 2019. V. 7. P. 95397–95417. https://doi.org/10.1109/ACCESS.2019.2928564.
7. Mohammed A. R., Mohammed S. A. and Shirmohammadi S. Machine Learning and Deep Learning Based Traffic Classification and Prediction in Software Defined Networking // Proc. 2019 IEEE International Symposium on Measurements & Networking (M&N). P. 1–6. https://doi.org/10.1109/IWMN.2019.8805044.
8. Mininet: An Instant Virtual Network on your Laptop (or other PC). URL: http://mininet.org/ (дата обращения: 01.02.2020).
9. Singhal P., Mathur R., Vyas H. State of the Art Review of Network Traffic Classification based on Machine Learning Approach // Proc. International Conference on Recent Trends in Engineer-ing & Technology, 2013. P. 12–15
10. Nguyen T., Grenville A. A survey of techniques for internet traffic classification using machine learning // IEEE Communications Surveys and Tutorials. 2008. V. 10. P. 56–76.
11. Patcha A. and Park J.-M. An overview of anomaly detection techniques: Existing solutions and latest technological trends // Computer Networks. 2007. V. 51, № 12. P. 3448–3470.
12. Latah M., Toker L. Artificial Intelligence Enabled Software Defined Networking: A Compre-hensive Overview // IET Networks. 2018. V. 8. https://doi.org/10.1049/iet-net.2018.5082.
13. Buczak A. L. and Guven E. A survey of data mining and machine learning methods for cyber security intrusion detection // IEEE Communications Surveys & Tutorials. 2016. V. 18, № 2.
P. 1153–1176.
14. Hodo E., Bellekens X. J., Hamilton A. W., Tachtatzis C., and Atkinson R. C. Shallow and Deep Networks Intrusion Detection System: A Taxonomy and Survey // ArXiv. 2017. abs/1701.02145.
15. Herrera A. J., Camargo J. E. A survey on machine learning applications for software defined network security // LNCS 11605. 2019. P. 70–96
16. Zhou X., Sun M., Li G. Y., and Juang B.-H. Machine learning and cognitive technology for in-telligent wireless networks // ArXiv. 2017. abs/1710.11240.
17. Chen M., Challita U., Saad W., Yin C., and Debbah M. Machine learning for wireless networks with artificial intelligence: A tutorial on neural networks // arXiv preprint arXiv:1710.02913, 2017.
18. Wang X., Li X., and Leung V. C. M. Artificial intelligence-based techniques for emerging heter-ogeneous network: State of the arts, opportunities, and challenges // IEEE Access. 2015. V. 3.
P. 1379–1391.
19. Klaine P. V., Imran M. A., Onireti O., and Souza R. D. A survey of machine learning techniques applied to self-organizing cellular networks // IEEE Communications Surveys & Tutorials. 2017. № 99. P. 1–1.
20. Haleplidis E., Pentikousis K., Denazis S. et al. Software-Defined Networking (SDN): Layers and Architecture Terminology, 2015. URL: https://tools.ietf.org/html/rfc7426 (дата обращения: 01.02.2020).
21. MVB da Silva, AS Jacobs, RJ Pfitscher, LZ Granville. IDEAFIX: Identifying elephant flows in P4-based IXP networks // Proc. 2018 IEEE Global Communications Conference (GLOBECOM). P. 1–6.
22. Ghulam Mohi-Ud-Din, Liu Zhi Qiang, Zhang Jiangbin. Data learning and traffic classification by Machine Learning // Proc. Academicsera 18th International Conference, Sydney, Australia, 2018.
23. Gomes R.L., Madeira M. E. R.: A traffic classification agent for virtual networks based on QoS classes // IEEE Latin Am. Trans. 2012. V. 10, № 3. P. 1734–1741.
24. Troia S., Martin N., Rodriguez A., Hernandez J. A., et al. Machine-learning-assisted routing in SDN-based optical networks // Proc. 44th European Conference on Optical Communication (ECOC), Rome, September 2018. https://doi.org/10.1109/ECOC.2018.8535437.
25. Pham Q.T., Hadjadj-Aoul Y., Outtagarts A. Deep Reinforcement Learning based QoS-aware Routing in Knowledge-defined networking // Proc. 14th EAI International Conference on Het-erogeneous Networking for Quality, Reliability, Security and Robustness (Qshine), Dec 2018, Ho Chi Minh City, Vietnam. P. 1–13.
26. Маньков В. А., Краснова И. А. Классификация потоков трафика SDN-сетей методами машинного обучения в режиме реального времени» // Труды международной научно-технической конференции «Информационные технологии и математическое моделиро-вание систем», 2019. С. 65–68. https://doi.org/10.36581/CITP.2019.31.51.016.
27. Lin S. Wang, Luo Min. A Framework for QoS-aware Traffic Classification Using Semi-supervised Machine Learning in SDNs // Proc. 2016 IEEE International Conference on Services Computing (SCC). P. 760–765. https://doi.org/10.1109/SCC.2016.
28. Singh K. Agrawal, S. Sohi B. A Near Real-time IP Traffic Classification Using Machine Learn-ing. International Journal of Intelligent Systems and Applications. 2013. V. 5. P. 83–93. https://doi.org/10.5815/ijisa.2013.03.09.
29. Iwai T., and Nakao A. Adaptive mobile application identification through in-network machine learning // Proc. 18th Asia-Pacific Network Operations and Management Symposium (APNOMS), 2016. P. 1–6. https://doi.org/10.1109/APNOMS.2016.7737226.
30. Saqib N. A., Shakeel Y., Khan M. A., Mehmood H., Zia M. An effective empirical approach to VoIP traffic classification // Turkish Journal of Electrical Engineering & Computer Sciences. 2017. V. 25, № 2. P. 888–900.
31. Huang N., Li C., Li C., Chen C., Chen C., and Hsu I. Application identification system for SDN QoS based on machine learning and DNS responses // Proc. 19th Asia-Pacific Network Operations and Management Symposium (APNOMS), 2017. P. 407–410. https://doi.org/
10.1109/APNOMS.2017.8094160.
32. Huang N., Jai G., Chao H., Tzang Y., and Chang H. Application traffic classification at the ear-ly stage by characterizing application rounds // Inf. Sci. 2013. V. 232. P. 130–142. https://doi.org/10.1016/j.ins.2012.12.039.
33. Anantavrasilp I., and Scholer T. Automatic flow classification using machine learning // Proc. 15th International Conference on Software, Telecommunications and Computer Networks, 2007. P. 1–6. https://doi.org/10.1109/SOFTCOM.2007.4446129.
34. Dong Y., Zhang M., Zhou R. Classification of Network Game Traffic Using Machine Learning. In: Yuan H., Geng J., Liu C., Bian F., Surapunt T. (eds) Geo-Spatial Knowledge and Intelli-gence. GSKI 2017. Communications in Computer and Information Science. V. 848. Springer, Singapore. https://doi.org/10.1007/978-981-13-0893-2_15.
35. Chhabra A., Kiran M. Classifying Elephant and Mice Flows, in High-Speed Scientific Net-works // Proc. 4th International Workshop on Innovating the Network for Data Intensive Sci-ence (INDIS), 2017.
36. Zhang C. Wang, X. Li F. He, Q. Huang Min. Deep learning-based network application classifi-cation for SDN // Transactions on Emerging Telecommunications Technologies. 2017.
V. 29. https://doi.org/10.1002/ett.3302.
37. Lotfollahi M., Jafari Siavoshani M., Shirali Hossein Zade R. et al. Deep Packet: A Novel Ap-proach For Encrypted Traffic Classifcation Using Deep Learning // Soft Computing. 2020.
V. 24. https://doi.org/10.1007/s00500-019-04030-2.
38. Jamuna A., Vinodh Ewards S. E. Efficient Flow based Network Traffic Classification using Machine Learning // International Journal of Engineering Research and Applications (IJERA). 2013. V. 3, Is. 2. P. 1324–1328.
39. Fan Z., Liu R. Investigation of machine learning based network traffic classification // Proc. In-ternational Symposium on Wireless Communication Systems (ISWCS), 2017. P. 1–6. https://doi.org/10.1109/ISWCS.2017.8108090.
40. Mestres A., Rodríguez-Natal A., Carner J., Barlet-Ros P., Alarcón E., Solé M., et al. Knowledge-Defined Networking // ArXiv. 2017. abs/1606.06222.
41. Parsaei M. R., Sobouti M. J., and Javidan R. Network Traffic Classification using Machine Learning Techniques over Software Defined Networks // International Journal of Advanced Computer Science and Applications. 2017. V. 8.
42. Changhe Y., Lan J., Xie J., Hu Y. QoS-aware traffic classification architecture using machine learning and deep packet inspection in SDNs // Proc. International congress of information and communication technology, 2018. P. 1209–1216.
43. Middleton S., Modafferi S. Scalable Classification of QoS for Real-Time Interactive Applica-tions from IP Traffic Measurements // Computer Networks. 2016. V. 107. P. 121–132.
44. Alharbi F. SDN-based mechanisms for provisioning quality of service to selected network flows // Theses and Dissertations: Computer Science. 2018. V. 72.
45. Aroussi S., and Mellouk A. Survey on machine learning-based QoE-QoS correlation models // Proc. International Conference on Computing, Management and Telecommunications (Com-ManTel), 2014. P. 200–204.
46. Alharbi F. SDN – Survey on Machine Learning-based QoE-QoS Correlation Models. An adap-tive machine learning-based QoE approach in SDN context for video-streaming services // The-ses and Dissertations: Computer Science. 2018. V. 72.
47. Caicedo O. M. Evalution de QoS usando tecnicas de machine learning. Universidad del Cauca, 2019. P. 19.
48. Letaifa A. B., Maher G., and Mouna S. ML based QoE enhancement in SDN context: Video streaming case // Proc. 13th International Wireless Communications and Mobile Computing Conference (IWCMC), 2017. P. 103–108.
49. Raumer D., Schwaighofer L., and Carle G. MonSamp: A distributed SDN application for QoS monitoring // Proc. Federated Conference on Computer Science and Information Systems, 2014. P. 961–968.
50. Huang N., Liao I., Liu H., Wu S., and Chou C. A dynamic QoS management system with flow classification platform for software-defined networks // Proc. 8th International Conference on Ubi-Media Computing (UMEDIA), 2015.
51. Sapio A., Canini M., Ho C., Nelson J., Kalnis P., Kim C., Krishnamurthy A., Moshref M., et al. Scaling Distributed Machine Learning with In-Network Aggregation // ArXiv, 2019. abs/1903.06701.
52. Zhang J., Chen C., Xiang Y., Zhou W., and Vasilakos, A.V. (2013). An Effective Network Traf-fic Classification Method with Unknown Flow Detection // IEEE Transactions on Network and Service Management. 2013. V. 10. P. 133–147.
53. Bakker J. N., Ng B., Seah W. K., and Pekár A. Traffic Classification with Machine Learning in a Live Network // Proc. IFIP/IEEE Symposium on Integrated Network and Service Management (IM), 2019. P. 488–493.
54. CAIDA Data – Overview of Datasets, Monitors, and Reports. URL: https://www.caida.org/data/overview/ (дата обращения: 01.02.2020).
55. SecRepo.com – Samples of Security Related Data. URL: http://www.secrepo.com/ (дата обращения: 01.02.2020).
56. ISCX Information Centre of Excellence for Tech Innovation. URL: http://www.iscx.ca/
datasets/ (дата обращения: 01.02.2020).
57. Машинное обучение вместо DPI. Строим классификатор трафика URL: https://habr.com/ru/post/304926/ (дата обращения: 01.02.2020).
58. Маньков В. А., Краснова И. А. Алгоритм динамической классификации потоков в муль-тисервисной SDN-сети // T-Comm: Телекоммуникации и транспорт. 2017. Т. 11, № 12.
С. 37–42.
59. Маньков В. А., Краснова И. А. Задача управления трафиком с динамическим определе-нием QoS в мультисервисных SDN сетях // Сборник трудов XI Международной отрас-левой научно-технической конференции «Технологии информационного общества», 15–16 марта 2017 г., МТУСИ. С. 67–68.
60. Mankov V. A., Krasnova I. A. Collection of Individual Packet Statistical Information in a Flow Based on P4-switch // Proc. Advances in Intelligent Systems and Computing. 2020. V. 1127. https://doi.org/10.1007/978-3-030-39216-1_11.
61. Машинное обучение для людей: Разбираемся простыми словами. URL: https://vas3k.ru/blog/machine_learning/ (дата обращения: 01.02.2020).

Ключевые слова

Machine Learning (ML), SDN, QoS, классификация трафика

Скачать полный текст