SSPC ALGORITHM BASED ON THREE DIFFERENT METHODS FOR ONLINE SKYPE TRAFFIC CLASSIFICATION

Classification of real time applications such as Skype and online games has gained more attention in the last few years. Most of the current Skype classification methods were only valid for offline classification. Each of the three common classification methods (port, payload, statistics based) has some limitations. To increase the quality of Internet traffic classifier, this paper combined the three methods to products a new classification algorithm (SSPC). In the proposed algorithm, each traffic flow was classified parallel three times by one of the three method classifiers. Based on some priority rules, SSPC makes classification decision for each flow. The SSPC algorithm was used to classify Skype traffic in two stages offline and online. The results of both cases shown, SSPC is the higher accuracy when compared with other classifiers. Also, the results indicate that the SSPC algorithm was suitable for online classification decision which is taken within capturing time