Research Article
BibTex RIS Cite

Traffic Classification and Comparative Analysis with Machine Learning Algorithms in Software Defined Networks

Year 2021, Volume: 9 Issue: 1, 71 - 83, 25.03.2021
https://doi.org/10.29109/gujsc.869418

Abstract

In computer networks, diverse applications generate network traffic with different characteristics. Network traffic classification is significant to manage networks better, improve service quality and ensure security. Software-Defined Networks (SDN) provides flexible and adaptable techniques for traffic classification with its programmable structure. SDN flows naturally exhibit particular characteristics of network applications and protocols. Therefore, it can be said that SDN can present significant opportunities in traffic classification using machine learning. This study proposes a traffic classification approach using machine learning models in SDN. In this study, DNS, Telnet, Ping and Voice traffic flows were created on the SDN using the Distributed Internet Traffic Generator (D-ITG) tool. Twelve-attributes representing these traffic flows (the number of packets transmitted, average transmission time, the number of instantly transmitted packets, etc.) were determined, and over the SDN controller in the physical network, a real-time data set was created by collecting data depending on the attributes. Later, the performance of k Nearest Neighbor (k-NN), Support Vector Machine (SVM), Multi-Layer Perceptron (MLP), Decision Tree (DT) and Naive Bayes (NB) machine learning models were tested for traffic classification on this data set. When the k-NN model was tested on this real-time data set, its classification accuracy was obtained as the maximum with 99.4%. Therefore this model has been determined as a machine learning giving the highest classification performance with the lowest cost flow attributes in traffic classification in SDN.

References

  • Tahaei, Hamid, et al. "The rise of traffic classification in IoT networks: A survey." Journal of Network and Computer Applications 154 (2020): 102538.
  • Nguyen, Thuy TT, and Grenville Armitage. "A survey of techniques for internet traffic classification using machine learning." IEEE communications surveys & tutorials 10.4 (2008): 56-76.
  • Dehghani, Fereshte, et al. "Real-time traffic classification based on statistical and payload content features." 2010 2nd International Workshop on Intelligent Systems and Applications. IEEE, 2010.
  • P. Barlet-Ros Co-Advisor and J. Solé-Pareta in, “Network Traffic Classification: From Theory to Practice Valentín Carela-Español,” no. October, 2014.
  • A. Mestres et al., “Public Review for Knowledge-Defined Networking,” ACM SIGCOMM Comput. Commun. Rev., vol. 47, no. 3, pp. 2–10, 2017.
  • F. Ieee et al., “Software-Defined Networking : A Comprehensive Survey,” vol. 103, no. 1, 2015.
  • OpenFlow Switch Specification v1.1.0. Available online: http://archive.openflow.org/documents/openflowspec- v1.1.0.pdf, Erişim Tarihi Ağustos, 20, 2019.
  • P. Wang, S. C. Lin, and M. Luo, “A framework for QoS-aware traffic classification using semi-supervised machine learning in SDNs,” in Proceedings - 2016 IEEE International Conference on Services Computing, SCC 2016, 2016, pp. 760–765, doi: 10.1109/SCC.2016.133.
  • D. Rossi and S. Valenti, “Fine-grained traffic classification with Netflow data,” IWCMC 2010 - Proc. 6th Int. Wirel. Commun. Mob. Comput. Conf., pp. 479–483, 2010, doi: 10.1145/1815396.1815507.
  • L. He, C. Xu, and Y. Luo, “VTC: Machine learning based traffic classification as a virtual network function,” SDN-NFV Secur. 2016 - Proc. 2016 ACM Int. Work. Secur. Softw. Defin. Networks Netw. Funct. Virtualization, co-located with CODASPY 2016, pp. 53–56, 2016, doi: 10.1145/2876019.2876029.
  • P. Amaral, J. Dinis, P. Pinto, L. Bernardo, J. Tavares, and H. S. Mamede, “Machine learning in software defined networks: Data collection and traffic classification,” in Proceedings - International Conference on Network Protocols, ICNP, 2016, vol. 2016-December, doi: 10.1109/ICNP.2016.7785327.
  • 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. 55380–55391, 2018, doi: 10.1109/ACCESS.2018.2872430.
  • H. K. Lim, J. B. Kim, K. Kim, Y. G. Hong, and Y. H. Han, “Payload-based traffic classification using multi-layer LSTM in software defined networks,” Appl. Sci., vol. 9, no. 12, 2019, doi: 10.3390/app9122550.
  • M. M. Raikar, S. M. Meena, M. M. Mulla, N. S. Shetti, and M. Karanandi, “Data Traffic Classification in Software Defined Networks (SDN) using supervised-learning,” Procedia Comput. Sci., vol. 171, no. 2019, pp. 2750–2759, 2020, doi: 10.1016/j.procs.2020.04.299.
  • D. Manual, A. Botta, W. De Donato, A. Dainotti, S. Avallone, and A. Pescap, “D-ITG 2.8.1 Manual,” pp. 1–35, 2013.
  • Scikit-learn Tutorials https://scikit-learn.org/stable/user_guide.html Erişim Tarihi Ağustos, 20, 2019.
  • S. Shekhar and H. Xiong, “Nearest Neighbor,” Encycl. GIS, vol. I, pp. 771–771, 2008, doi: 10.1007/978-0-387-35973-1_862.
  • Nello Cristianini and John Shawe-Taylor. An introduction to Support Vector Machines and Other Kernel-based Learning Methods. Cambridge University Press, New York, NY, 1999

Yazılım Tanımlı Ağlarda Makine Öğrenme Algoritmaları ile Trafik Sınıflandırma ve Karşılaştırmalı Analiz

Year 2021, Volume: 9 Issue: 1, 71 - 83, 25.03.2021
https://doi.org/10.29109/gujsc.869418

Abstract

Bilgisayar ağlarında, farklı uygulamalar farklı özelliklere sahip ağ trafiği üretirler. Ağları daha iyi yönetmek, hizmet kalitesini artırmak ve güvenliği sağlamak için ağ trafiğinin sınıflandırılması önemlidir. Yazılım Tanımlı Ağlar (YTA) programlanabilir yapısı ile trafik sınıflandırması için esnek ve uyarlanabilir teknikler sağlar. YTA akışları doğal olarak ağ uygulamaları ve protokollerinin belirli özelliklerini sergiler. Dolaysıyla, YTA’ nın makine öğrenmesi kullanarak trafik sınıflandırmada önemli fırsatlar sunduğu söylenebilir. Bu çalışmada, YTA’ da makine öğrenme modellerini kullanarak bir trafik sınıflandırma yaklaşımı öneriyoruz. Dağıtık İnternet Trafik Oluşturucu (D-ITG) aracı kullanılarak YTA üzerinde DNS, Telnet, Ping ve Ses trafik akışları oluşturulmuştur. Bu trafik akışlarını temsil eden on iki öznitelik (iletilen paket sayısı, ortalalama iletim süresi, anlık iletilen paket sayısı vb.) belirlendi ve fiziksel ağdaki YTA kontrolcüsü üzerinden gerçek zamanlı olarak özniteliklere ait veriler toplanarak bir veri seti oluşturuldu. Daha sonra da bu veri seti üzerinde trafik sınıflandırması için k En Yakın Komşu, Destek Vektör Makinesi, Çok Katmanlı Algılayıcı, Karar Ağacı ve Naive Bayes makine öğrenme modellerinin başarımı test edildi. Gerçek zamanlı olarak oluşturulan bu veri seti üzerinde k En Yakın Komşu modeli kullanıldığında %99.4 doğruluk oranı ile en yüksek sınıflandırma doğruluğu elde edilmiştir. Dolayısıyla, YTA’da trafik sınıflandırmasında, en düşük maliyetli akış öznitelikleri ile en yüksek sınıflandırma performansı veren makine öğrenme modeli olduğu tespit edilmiştir.

References

  • Tahaei, Hamid, et al. "The rise of traffic classification in IoT networks: A survey." Journal of Network and Computer Applications 154 (2020): 102538.
  • Nguyen, Thuy TT, and Grenville Armitage. "A survey of techniques for internet traffic classification using machine learning." IEEE communications surveys & tutorials 10.4 (2008): 56-76.
  • Dehghani, Fereshte, et al. "Real-time traffic classification based on statistical and payload content features." 2010 2nd International Workshop on Intelligent Systems and Applications. IEEE, 2010.
  • P. Barlet-Ros Co-Advisor and J. Solé-Pareta in, “Network Traffic Classification: From Theory to Practice Valentín Carela-Español,” no. October, 2014.
  • A. Mestres et al., “Public Review for Knowledge-Defined Networking,” ACM SIGCOMM Comput. Commun. Rev., vol. 47, no. 3, pp. 2–10, 2017.
  • F. Ieee et al., “Software-Defined Networking : A Comprehensive Survey,” vol. 103, no. 1, 2015.
  • OpenFlow Switch Specification v1.1.0. Available online: http://archive.openflow.org/documents/openflowspec- v1.1.0.pdf, Erişim Tarihi Ağustos, 20, 2019.
  • P. Wang, S. C. Lin, and M. Luo, “A framework for QoS-aware traffic classification using semi-supervised machine learning in SDNs,” in Proceedings - 2016 IEEE International Conference on Services Computing, SCC 2016, 2016, pp. 760–765, doi: 10.1109/SCC.2016.133.
  • D. Rossi and S. Valenti, “Fine-grained traffic classification with Netflow data,” IWCMC 2010 - Proc. 6th Int. Wirel. Commun. Mob. Comput. Conf., pp. 479–483, 2010, doi: 10.1145/1815396.1815507.
  • L. He, C. Xu, and Y. Luo, “VTC: Machine learning based traffic classification as a virtual network function,” SDN-NFV Secur. 2016 - Proc. 2016 ACM Int. Work. Secur. Softw. Defin. Networks Netw. Funct. Virtualization, co-located with CODASPY 2016, pp. 53–56, 2016, doi: 10.1145/2876019.2876029.
  • P. Amaral, J. Dinis, P. Pinto, L. Bernardo, J. Tavares, and H. S. Mamede, “Machine learning in software defined networks: Data collection and traffic classification,” in Proceedings - International Conference on Network Protocols, ICNP, 2016, vol. 2016-December, doi: 10.1109/ICNP.2016.7785327.
  • 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. 55380–55391, 2018, doi: 10.1109/ACCESS.2018.2872430.
  • H. K. Lim, J. B. Kim, K. Kim, Y. G. Hong, and Y. H. Han, “Payload-based traffic classification using multi-layer LSTM in software defined networks,” Appl. Sci., vol. 9, no. 12, 2019, doi: 10.3390/app9122550.
  • M. M. Raikar, S. M. Meena, M. M. Mulla, N. S. Shetti, and M. Karanandi, “Data Traffic Classification in Software Defined Networks (SDN) using supervised-learning,” Procedia Comput. Sci., vol. 171, no. 2019, pp. 2750–2759, 2020, doi: 10.1016/j.procs.2020.04.299.
  • D. Manual, A. Botta, W. De Donato, A. Dainotti, S. Avallone, and A. Pescap, “D-ITG 2.8.1 Manual,” pp. 1–35, 2013.
  • Scikit-learn Tutorials https://scikit-learn.org/stable/user_guide.html Erişim Tarihi Ağustos, 20, 2019.
  • S. Shekhar and H. Xiong, “Nearest Neighbor,” Encycl. GIS, vol. I, pp. 771–771, 2008, doi: 10.1007/978-0-387-35973-1_862.
  • Nello Cristianini and John Shawe-Taylor. An introduction to Support Vector Machines and Other Kernel-based Learning Methods. Cambridge University Press, New York, NY, 1999
There are 18 citations in total.

Details

Primary Language English
Subjects Engineering
Journal Section Tasarım ve Teknoloji
Authors

Özgür Tonkal 0000-0001-7219-9053

Hüseyin Polat 0000-0003-4128-2625

Publication Date March 25, 2021
Submission Date January 27, 2021
Published in Issue Year 2021 Volume: 9 Issue: 1

Cite

APA Tonkal, Ö., & Polat, H. (2021). Traffic Classification and Comparative Analysis with Machine Learning Algorithms in Software Defined Networks. Gazi University Journal of Science Part C: Design and Technology, 9(1), 71-83. https://doi.org/10.29109/gujsc.869418

                                TRINDEX     16167        16166    21432    logo.png

      

    e-ISSN:2147-9526