Internet Traffic Identification Using Community Detecting Algorithm

In recent years, Internet traffic classification using machine learning has become a new direction in network measurement. Because supervised clustering algorithm need accuracy of training sets and it can not classify unknown application, we introduced complex network´s community detecting algorithm, a new unsupervised classify algorithm, which have previously not been used for network traffic classification. We evaluate this algorithm and compare it to the previously used unsupervised K-means and DBSCAN algorithm, using empirical Internet traces. The experiment results show complex network´s community detecting algorithm work very well in accuracy and produces better clusters, besides, complex network´s community detecting algorithm need not know the number of the traffic application beforehand.