A Comparison of Supervised Machine Learning Algorithms for Classification of Communications Network Traffic
Automated network traffic classification is a basic requirement for managing Quality of Service in communications networks. This research compares the performance of six widely-used supervised machine learning algorithms for classifying network traffic. The evaluations were conducted for classification of five distinct network traffic classes and two feature selection techniques. Our comparative results show that the Random Forest and Decision Tree algorithms are promising classifiers for network traffic in terms of both classification accuracy and computational efficiency.
KeywordsClassification Network traffic Machine learning QoS Random Forest Decision Trees
This work was supported in part by the Australian Research Council (ARC) under the Discovery Project scheme (Grant Nos. DP160102571 and DP170103305).
- 1.Waikato environment for knowledge analysis (weka), version 3.6.6 (c), 1999–2011. The University of Waikato, Hmilton, New Zealand. http://www.cs.waikato.ac.nz/~ml/weka/
- 5.Kira, K., Rendell, L.A.: A practical approach to feature selection. In: Proceedings of the Ninth International Workshop on Machine Learning, ML92, pp. 249–256. Morgan Kaufmann Publishers Inc., San Francisco (1992)Google Scholar
- 7.Li, W., Moore, A.W.: A machine learning approach for efficient traffic classification. In: 2007 15th International Symposium on Modeling, Analysis, and Simulation of Computer and Telecommunication Systems. Institute of Electrical and Electronics Engineers (IEEE) (2007)Google Scholar
- 8.Li, Z., Yuan, R., Guan, X.: Accurate classification of the internet traffic based on the SVM method. In: 2007 IEEE International Conference on Communications. IEEE (2007)Google Scholar
- 9.Munther, A., Othman, R.R., Alsaadi, A.S., Anbar, M.: A performance study of hidden Markov model and random forest in internet traffic classification. In: Kim, K., Joukov, N. (eds.) Information Science and Applications (ICISA) 2016. LNEE, vol. 376, pp. 319–329. Springer, Singapore (2016). doi: 10.1007/978-981-10-0557-2_32 CrossRefGoogle Scholar
- 12.Peng, L., Yang, B., Chen, Y.: Hierarchical RBF neural network using for early stage internet traffic identification. In: 2014 IEEE 17th International Conference on Computational Science and Engineering. Institute of Electrical and Electronics Engineers (IEEE) (2014)Google Scholar
- 13.Risso, F., Baldi, M., Morandi, O., Baldini, A., Monclus, P.: Lightweight, payload-based traffic classification: an experimental evaluation. In: 2008 IEEE International Conference on Communications. IEEE (2008)Google Scholar
- 15.Rouhi, R., Farshid, K., Amiri, M.: Improving the intrusion detection systems’ performance by correlation as a sample selection method. J. Comput. Sci. Appl. 1(3), 33–38 (2013)Google Scholar