research_article

Machine Learning-Driven Traffic Classification in Software-Defined Networks: A Comprehensive Review of Feature Selection Methods and Classification Algorithms

Volume1
Issue1
Pages34-50
DOI#
Abstract

The rapid growth of network traffic and the increasing use of encrypted applications have made traditional traffic classification methods such as port-based techniques and deep packet inspection less effective. Software-Defined Networking (SDN) provides centralized control and programmability, enabling advanced traffic management when combined with machine learning (ML). This study reviews and evaluates the performance of ML algorithms for network traffic classification in SDN environments.
Experiments were conducted using the UNB ISCX Network Traffic Dataset containing multiple traffic categories such as CHAT, FILE, STREAMING, VIDEO, AUDIO, and MAIL. Three machine learning models—Random Forest (RF), Support Vector Machine (SVM), and Logistic Regression (LR)—were implemented. Recursive Feature Elimination with Cross-Validation (RFECV) was applied for optimal feature selection and to reduce overfitting. Model performance was evaluated using accuracy, precision, recall, and F1-score.
Results show that Random Forest achieved the best performance with 97.49% accuracy and a macro F1-score of 0.97, followed by SVM with 95.55% accuracy and Logistic Regression with 92.87%. Feature selection significantly improved classification performance and model generalization, particularly in handling imbalanced traffic classes.
The study concludes that Random Forest combined with RFECV-based feature selection provides an effective solution for accurate and efficient traffic classification in SDN. The integration of machine learning with SDN can improve network security, quality of service, and resource management.

Keywords
Software-Defined Networking (SDN)Network Traffic ClassificationMachine LearningRandom ForestSupport Vector MachineLogistic RegressionFeature SelectionRFECVImbalanced DataNetwork Security.
Download Article PDF
References
  1. Ahmed, A. A., & Agunsoye, G. (2021). A real-time network traffic classifier for online applications using machine learning. Algorithms, 14(8), 250. https://doi.org/10.3390/a14080250
  2. AlZoman, R. M., & Alenazi, M. J. F. (2021). A comparative study of traffic classification techniques for smart city networks. Sensors, 21(14), 4677. https://doi.org/10.3390/s21144677
  3. Amaral, P., Dinis, J., Pinto, P., Bernardo, L., Tavares, J., & Mamede, H. S. (2016). Machine learning in software defined networks: Data collection and traffic classification. In 2016 IEEE 24th International Conference on Network Protocols (ICNP) (pp. 1-5). IEEE. https://doi.org/10.1109/ICNP.2016.7785327
  4. Belkadi, O., Vulpe, A., Laaziz, Y., & Halunga, S. (2023). ML-based traffic classification in an SDN-enabled cloud environment. Electronics, 12(2), 269. https://doi.org/10.3390/electronics12020269
  5. Cortes, C., & Vapnik, V. (1995). Support-vector networks. Machine Learning, 20(3), 273-297. https://doi.org/10.1007/BF00994018
  6. Eldhai, A. M., Hamdan, M., Khan, S., Hamzah, M., & Marsono, M. N. (2022). Traffic classification based on incremental learning algorithms for the software-defined networks. In 2022 International Conference on Frontiers of Information Technology (FIT) (pp. 338-343). IEEE. https://doi.org/10.1109/FIT57066.2022.00067
  7. Eldhai, A. M., et al. (2024). Improved feature selection and stream traffic classification based on machine learning in software-defined networks. IEEE Access, 12, 12345-12360. https://doi.org/10.1109/ACCESS.2024.3356789
  8. Farhady, H., Lee, H., & Nakao, A. (2015). Software-defined networking: A survey. Computer Networks, 81, 79-95. https://doi.org/10.1016/j.comnet.2015.01.018
  9. Hosmer, D. W., Lemeshow, S., & Sturdivant, R. X. (2013). Applied logistic regression (3rd ed.). John Wiley & Sons.
  10. Huo, L., Jiang, D., Qi, S., & Miao, L. (2021). A blockchain-based security traffic measurement approach to software defined networking. Mobile Networks and Applications, 26, 586-596. https://doi.org/10.1007/s11036-019-01467-5
  11. Khan, F. A., & Ibrahim, A. A. (2024). Machine learning-based enhanced deep packet inspection for IP packet priority classification with differentiated services code point for advance network management. Journal of Telecommunication, Electronic and Computer Engineering, 16(2), 5-12.
  12. Latah, M., & Toker, L. (2016). Application of artificial intelligence to software defined networking: A survey. Indian Journal of Science and Technology, 9(44), 1-7. https://doi.org/10.17485/ijst/2016/v9i44/105259
  13. Le, L.-V., Lin, B.-S., & Do, S. (2018). Applying big data, machine learning, and SDN/NFV for 5G early-stage traffic classification and network QoS control. Transactions on Networks and Communications, 6(2), 36. https://doi.org/10.14738/tnc.62.4321
  14. Li, Y., & Li, J. (2014). MultiClassifier: A combination of DPI and ML for application-layer classification in SDN. In The 2014 2nd International Conference on Systems and Informatics (ICSAI 2014) (pp. 682-686). IEEE. https://doi.org/10.1109/ICSAI.2014.7009375
  15. Ng, B., Hayes, M., & Seah, W. K. G. (2015). Developing a traffic classification platform for enterprise networks with SDN: Experiences & lessons learned. In 2015 IFIP Networking Conference (IFIP Networking) (pp. 1-9). IEEE. https://doi.org/10.1109/IFIPNetworking.2015.7145315
  16. Qazi, Z. A., Lee, J., Jin, T., Bellala, G., Arndt, M., & Noubir, G. (2013). Application-awareness in SDN. In Proceedings of the ACM SIGCOMM 2013 Conference on SIGCOMM (pp. 487-488). ACM. https://doi.org/10.1145/2486001.2491700
  17. Ren, K., Zeng, Y., Cao, Z., & Zhang, Y. (2022). ID-RDRL: A deep reinforcement learning-based feature selection intrusion detection model. Scientific Reports, 12(1), 15370. https://doi.org/10.1038/s41598-022-19340-3
  18. Restuccia, F., D'oro, S., & Melodia, T. (2018). Securing the internet of things in the age of machine learning and software-defined networking. IEEE Internet of Things Journal, 5(6), 4829-4842. https://doi.org/10.1109/JIOT.2018.2846040
  19. Rigatti, S. J. (2017). Random forest. Journal of Insurance Medicine, 47(1), 31-39. https://doi.org/10.17849/insm-47-01-31-39.1
  20. Rowshanrad, S., Namvarasl, S., Abdi, V., Hajizadeh, M., & Keshtgari, M. (2014). A survey on SDN, the future of networking. Journal of Advanced Computer Science & Technology, 3(2), 232-248. https://doi.org/10.14419/jacst.v3i2.3754
  21. Sabbeth, A., Al-Dunainawi, Y., Al-Raweshidy, H. S., & Abbod, M. F. (2016). Performance prediction of software defined network using an artificial neural network. In 2016 SAI Computing Conference (SAI) (pp. 80-84). IEEE. https://doi.org/10.1109/SAI.2016.7555966
  22. SE, V. E. (2013). Survey of traffic classification using machine learning. International Journal of Advanced Research in Computer Science, 4(4), 13.
  23. Sezer, S., et al. (2013). Are we ready for SDN? Implementation challenges for software-defined networks. IEEE Communications Magazine, 51(7), 36-43. https://doi.org/10.1109/MCOM.2013.6553676
  24. Sharma, N. V., & Yadav, N. S. (2021). An optimal intrusion detection system using recursive feature elimination and ensemble of classifiers. Microprocessors and Microsystems, 85, 104293. https://doi.org/10.1016/j.micpro.2021.104293
  25. Shu, Z., Wan, J., Li, D., Lin, J., Vasilakos, A. V., & Imran, M. (2016). Security in software-defined networking: Threats and countermeasures. Mobile Networks and Applications, 21, 764-776. https://doi.org/10.1007/s11036-016-0676-8
  26. Tonni, Z. A., & Mazumder, R. (2023). A novel feature selection technique for intrusion detection system using RF-RFE and bio-inspired optimization. In 2023 57th Annual Conference on Information Sciences and Systems (CISS) (pp. 1-6). IEEE. https://doi.org/10.1109/CISS56502.2023.10089745
  27. Ustebay, S., Turgut, Z., & Aydin, M. A. (2018). Intrusion detection system with recursive feature elimination by using random forest and deep learning classifier. In 2018 International Congress on Big Data, Deep Learning and Fighting Cyber Terrorism (IBIGDELFT) (pp. 71-76). IEEE. https://doi.org/10.1109/IBIGDELFT.2018.8625318
  28. Vassilaras, S., et al. (2018). Problem-adapted artificial intelligence for online network optimization. arXiv preprint arXiv:1805.12090.
  29. Wang, P., Lin, S.-C., & Luo, M. (2016). A framework for QoS-aware traffic classification using semi-supervised machine learning in SDNs. In 2016 IEEE International Conference on Services Computing (SCC) (pp. 760-765). IEEE. https://doi.org/10.1109/SCC.2016.110
  30. Wang, Y., Jiang, D., Huo, L., & Zhao, Y. (2021). A new traffic prediction algorithm to software defined networking. Mobile Networks and Applications, 26, 716-725. https://doi.org/10.1007/s11036-019-01417-1
  31. Wintano, J. N., & Lim, H. (2019). Software-defined networking application with deep deterministic policy gradient. In Proceedings of the 11th International Conference on Computer Modeling and Simulation (pp. 176-179). ACM. https://doi.org/10.1145/3307363.3307389
  32. Xiao, P., et al. (2016). A traffic classification method with spectral clustering in SDN. In 2016 17th International Conference on Parallel and Distributed Computing, Applications and Technologies (PDCAT) (pp. 391-394). IEEE. https://doi.org/10.1109/PDCAT.2016.088
  33. Yan, J., & Yuan, J. (2018). A survey of traffic classification in software defined networks. In *2018 1st IEEE International Conference on Hot Information-Centric Networking (HotICN)* (pp. 200-206). IEEE. https://doi.org/10.1109/HOTICN.2018.8605990
Scroll to Top