Traffic identification method based on on-line density based spatial clustering algorithm

Recently traffic identification based on Machine Learning (ML) techniques has attracted a great deal of interest. Two challenging issues for these methods are how to deal with encrypted flows and cope with the rapid growing number of new application types correctly and early. We propose a hybrid traffic identification method and a novel unsupervised clustering algorithm, On-Line Density Based Spatial Clustering (OLDBSC) algorithm, in which flows are automatically clustered based on sub-flow statistical features instead of full flows. We select Best-first features algorithm to find an optimal feature-sets, and then map the clusters to application types based on maximum probabilities applications in the clusters. The experiment results demonstrate that the proposed hybrid traffic identification method and OLDBSC algorithm is capable of identifying encrypted flows and potential new application types.