Therefore, one approach is to combine the advantages of different identification methods, in order to improve the completeness and accuracy of classification. In this study we compare and benchmark the currently known traffic classification methods on network traces captured in an operational 3G mobile network. Utilizing the experiences about the strengths and weaknesses of the existing approaches, a novel traffic classification method is proposed. The novel method is based on a complex decision mechanism, in order to provide appropriate identification for each different application type. As main result, the ratio of the unclassified traffic becomes significantly lower. Further, the reliability of the classification improves, as the various methods validate the results of each other. The novel method is tested on passive measurements of an operational mobile broadband network, and it is presented how the proposed solution improves traffic classification, when compared to existing methods. As a main contribution, it is shown that applications previously used only in fixed access networks may appear in mobile broadband environment.
Authors
G. Szabó, D. Orincsay, B. Peter Gerõ, S. Gyõri, T. Borsos