The Network Topology Classification in SDN Ecosystem using Machine Learning


Jyoti Yadav


To meet the increasing network demands of enterprise environments and data centers, traditional network architectures have been replaced by software-enabled hardware devices for developing agile, dynamic, and programmable networks. Software Defined Networking (SDN) is a new paradigm shift that abstracts network design and infrastructure in the software and then implements it by using software across hardware devices. SDN is used to build and manage the network in a customized way. SDN architecture offers network virtualization, network programmability, and flexibility by decoupling control and data planes which further enriches the network performance. As such, the SDN controller is a tactical control point in SDN. An SDN normally allows data flow control to the switches and/or routers and the rationale of the application's logic for deploying intelligent networks. SDN with Machine Learning (ML) and Artificial Intelligence (AI) techniques build network models, which essentially can take decisions based on self-learning and self-management capabilities. Accurate classification of topology is of prime importance to satisfy future network prerequisites like unpredictable traffic patterns, dynamic scaling, flexibility, and centralized control. The controller needs to have exact information about the topology of the network in order to configure and manage the network. Subsequently, topology classification is an important component of any Software Defined Network architecture. This paper presents the classification of topologies using different supervised ML algorithms. The accuracy obtained from Support Vector Machine (SVM) and Classification and Regression (CART) is 95% and 90% respectively. 

The experimental results show that according to the k Cross-Fold validation technique, SVM algorithm has been found to be the most accurate amongst the other ML algorithms with a mean accuracy value of 85%.


How to Cite
AHIRE, K., & Yadav, J. . . (2022). The Network Topology Classification in SDN Ecosystem using Machine Learning. International Journal of Next-Generation Computing, 13(2).


  1. Bel, L., Allard, D., Laurent, J.-M., Cheddadi, R., and Bar-Hen, A. 2009. Cart algorithm
  2. for spatial data: Application to environmental and ecological data. Computational
  3. Statistics & Data Analysis 53, 8, 3082–3093.
  4. Benzekki, K., El Fergougui, A., and Elbelrhiti Elalaoui, A. 2016. Software-defined
  5. networking (sdn): a survey. Security and communication networks 9, 18, 5803–5833.
  6. Bernaille, L., Teixeira, R., Akodkenou, I., Soule, A., and Salamatian, K. 2006. Traffic
  7. classification on the fly. ACM SIGCOMM Computer Communication Review 36, 2, 23–26.
  8. Gupta, A. ., & Prabhat, P. . (2017). Novel Approaches in Network Fault Management. International Journal of Next-Generation Computing, 8(2), 115–126.
  9. Bholebawa, I. Z. and Dalal, U. D. 2016. Design and performance analysis of openflowenabled
  10. network topologies using mininet. International Journal of Computer and Communication
  11. Engineering 5, 6, 419.
  12. Boumerdassi, S., Renault, ´E., and M¨uhlethaler, P. 2020. Machine Learning for Networking:
  13. Second IFIP TC 6 International Conference, MLN 2019, Paris, France, December 3–5,
  14. , Revised Selected Papers. Vol. 12081. Springer Nature.
  15. Buathong, W. and Meesad, P. 2013. Enhancing the efficiency of dimensionality reduction
  16. using a combined linear svm weight with relieff feature selection method. In The 9th
  17. International Conference on Computing and InformationTechnology (IC2IT2013). Springer,
  18. –134.
  19. Buczak, A. L. and Guven, E. 2015. A survey of data mining and machine learning methods
  20. for cyber security intrusion detection. IEEE Communications surveys & tutorials 18, 2,
  21. –1176.
  22. Calcaterra, C., Carmenini, A., Marotta, A., Bucci, U., and Cassioli, D. 2020. Maxhadoop:
  23. an efficient scalable emulation tool to test sdn protocols in emulated hadoop
  24. environments. Journal of Network and Systems Management 28, 4, 1610–1638.
  25. Crichton, N. J., Hinde, J. P., and Marchini, J. 1997. Models for diagnosing chest pain: is
  26. cart helpful? Statistics in Medicine 16, 7, 717–727.
  27. Dainotti, A., Pescape, A., and Claffy, K. C. 2012. Issues and future directions in traffic
  28. classification. IEEE network 26, 1, 35–40.
  29. Fadlullah, Z. M., Tang, F., Mao, B., Kato, N., Akashi, O., Inoue, T., and Mizutani,
  30. K. 2017. State-of-the-art deep learning: Evolving machine intelligence toward tomorrow’s
  31. intelligent network traffic control systems. IEEE Communications Surveys &
  32. Tutorials 19, 4, 2432–2455.
  33. Gupta, A. Network Management: Current Trends and Future Perspectives. J Netw Syst Manage 14, 483–491 (2006). DOI:
  34. Ghosh, S., Dasgupta, A., and Swetapadma, A. 2019. A study on support vector machine
  35. based linear and non-linear pattern classification.
  36. Gray, N., Dietz, K., and Hossfeld, T. 2020. Simulative evaluation of kpis in sdn for topology
  37. classification and performance prediction models. In 2020 16th International Conference
  38. on Network and Service Management (CNSM). IEEE, 1–9.
  39. Hakiri, A., Gokhale, A., Berthou, P., Schmidt, D. C., and Gayraud, T. 2014. Softwaredefined
  40. networking: Challenges and research opportunities for future internet. Computer
  41. Networks 75, 453–471.
  42. Islam, M., Islam, N., Refat, M., et al. 2020. Node to node performance evaluation through
  43. ryu sdn controller. Wireless Personal Communications 112, 1, 555–570.
  44. Jadhav, S. D. and Channe, H. 2016. Efficient recommendation system using decision tree
  45. classifier and collaborative filtering. Int. Res. J. Eng. Technol 3, 8, 2113–2118.
  46. Joachims, T. et al. 1999. Transductive inference for text classification using support vector
  47. machines. In Icml. Vol. 99. 200–209.
  48. Kotsiantis, S. B., Zaharakis, I., Pintelas, P., et al. 2007. Supervised machine learning: A
  49. review of classification techniques. Emerging artificial intelligence applications in computer
  50. engineering 160, 1, 3–24.
  51. Kumar, S., Ratnoo, S., and Vashishtha, J. 2021. Hyper heuristic evolutionary approach for
  52. constructing decision tree classifiers. Journal of Information and Communication Technology
  53. , 2, 249–276.
  54. Lemon, S. C., Roy, J., Clark, M. A., Friedmann, P. D., and Rakowski, W. 2003.
  55. Classification and regression tree analysis in public health: methodological review and
  56. comparison with logistic regression. Annals of behavioral medicine 26, 3, 172–181.
  57. Li, Y. and Guo, L. 2008. Tcm-knn scheme for network anomaly detection using feature-based
  58. optimizations. In Proceedings of the 2008 ACM symposium on applied computing. 2103–
  59. Lin, P., Bi, J., Wolff, S., Wang, Y., Xu, A., Chen, Z., Hu, H., and Lin, Y. 2015. A
  60. west-east bridge based sdn inter-domain testbed. IEEE Communications Magazine 53, 2,
  61. –197.
  62. Liu, C., Malboubi, A., and Chuah, C.-N. 2016. Openmeasure: Adaptive flow measurement
  63. & inference with online learning in sdn. In 2016 IEEE Conference on Computer Communications
  64. Workshops (INFOCOM WKSHPS). IEEE, 47–52.
  65. Liu, Y.-F., Guo, J.-M., and Lee, J.-D. 2011. Halftone image classification using lms algorithm
  66. and naive bayes. IEEE Transactions on Image Processing 20, 10, 2837–2847.
  67. MurphyMc. 2011. The nox controller. ”". [Online; Accessed
  68. Aug 2020.].
  69. Nguyen, T. T. and Armitage, G. 2008. A survey of techniques for internet traffic classification
  70. using machine learning. IEEE communications surveys & tutorials 10, 4, 56–76.
  71. Nsnam. 2020. Ns-3. ”". [Online; Accessed 11 May 2020.].
  72. Osuna, E., Freund, R., and Girosit, F. 1997. Training support vector machines: an application
  73. to face detection. In Proceedings of IEEE computer society conference on computer
  74. vision and pattern recognition. IEEE, 130–136.
  75. Polat, O. and Polat, H. 2020. An intelligent software defined networking controller component
  76. to detect and mitigate denial of service attacks. Journal of Information and Communication
  77. Technology 20, 1, 57–81.
  78. Project, M. 2018. Mininet overview. ”". [Online; Accessed 19-July-
  79. .
  80. project team, R. 2014. Ryu sdn framework. ”". [Online;
  81. Accessed 11 Nov 2019.].
  82. Raikar, M. M., Meena, S., Mulla, M. M., Shetti, N. S., and Karanandi, M. 2020. Data
  83. traffic classification in software defined networks (sdn) using supervised-learning. ProcediaComputer Science 171, 2750–2759.
  84. Scarfone, K., Mell, P., et al. 2007. Guide to intrusion detection and prevention systems
  85. (idps). NIST special publication 800, 2007, 94.
  86. Scholkopf, B., Sung, K.-K., Burges, C. J., Girosi, F., Niyogi, P., Poggio, T., and
  87. Vapnik, V. 1997. Comparing support vector machines with gaussian kernels to radial
  88. basis function classifiers. IEEE transactions on Signal Processing 45, 11, 2758–2765.
  89. Shalimov, A., Zuikov, D., Zimarina, D., Pashkov, V., and Smeliansky, R. 2013. Advanced
  90. study of sdn/openflow controllers. In Proceedings of the 9th central & eastern
  91. european software engineering conference in russia. 1–6.
  92. Song, C., Park, Y., Golani, K., Kim, Y., Bhatt, K., and Goswami, K. 2017. Machinelearning
  93. based threat-aware system in software defined networks. In 2017 26th international
  94. conference on computer communication and networks (ICCCN). IEEE, 1–9.
  95. Tian, Y., Shi, Y., and Liu, X. 2012. Recent advances on support vector machines research.
  96. Technological and economic development of Economy 18, 1, 5–33.
  97. Vedala, R. and Kumar, B. R. 2012. An application of naive bayes classification for credit scoring
  98. in e-lending platform. In 2012 International Conference on Data Science & Engineering
  99. (ICDSE). IEEE, 81–84.
  100. Vitaliy. 2012. The nox controller. ”". [Online; Accessed 21
  101. Nov 2020.].
  102. Walter, M., Alizadeh, S., Jamalabadi, H., Lueken, U., Dannlowski, U., Walter, H.,
  103. Olbrich, S., Colic, L., Kambeitz, J., Koutsouleris, N., et al. 2019. Translational
  104. machine learning for psychiatric neuroimaging. Progress in Neuro-Psychopharmacology and
  105. Biological Psychiatry 91, 113–121.
  106. Wan, V. and Campbell, W. M. 2000. Support vector machines for speaker verification and
  107. identification. In Neural Networks for Signal Processing X. Proceedings of the 2000 IEEE
  108. Signal Processing Society Workshop (Cat. No. 00TH8501). Vol. 2. IEEE, 775–784.
  109. Xie, J., Guo, D., Hu, Z., Qu, T., and Lv, P. 2015. Control plane of software defined networks:
  110. A survey. Computer communications 67, 1–10.
  111. Zamani, M., Movahedi, M., Ebadzadeh, M., and Pedram, H. 2009. A ddos-aware ids
  112. model based on danger theory and mobile agents. In 2009 International Conference on
  113. Computational Intelligence and Security. Vol. 1. IEEE, 516–520.
  114. Zhai, Y. and Zheng, X. 2018. Random forest based traffic classification method in sdn. In
  115. International Conference on Cloud Computing, Big Data and Blockchain (ICCBB).
  116. IEEE, 1–5.
  117. Zhang, J., X. Y. Z. W. and Wang, Y. 2013. Unsupervised traffic classification using
  118. flow statistical properties and ip packet payload. Journal of Computer and System Sciences
  119. , pp.573-585.
  120. Zhao, Y., Li, Y., Zhang, X., Geng, G., Zhang, W., and Sun, Y. 2019. A survey of
  121. networking applications applying the software defined networking concept based on machine
  122. learning. IEEE Access 7, 95397–95417.
  123. Zhu, L., Karim, M. M., Sharif, K., Li, F., Du, X., and Guizani, M. 2019. Sdn controllers:
  124. Benchmarking & performance evaluation. arXiv preprint arXiv:1902.04491 .