• KSII Transactions on Internet and Information Systems
    Monthly Online Journal (eISSN: 1976-7277)

Classification of Traffic Flows into QoS Classes by Unsupervised Learning and KNN Clustering

Vol. 3, No. 2, April 24, 2009
10.3837/tiis.2009.02.001, Download Paper (Free):

Abstract

Traffic classification seeks to assign packet flows to an appropriate quality of service (QoS) class based on flow statistics without the need to examine packet payloads. Classification proceeds in two steps. Classification rules are first built by analyzing traffic traces, and then the classification rules are evaluated using test data. In this paper, we use self-organizing map and K-means clustering as unsupervised machine learning methods to identify the inherent classes in traffic traces. Three clusters were discovered, corresponding to transactional, bulk data transfer, and interactive applications. The K-nearest neighbor classifier was found to be highly accurate for the traffic data and significantly better compared to a minimum mean distance classifier.


Statistics

Show / Hide Statistics

Statistics (Cumulative Counts from December 1st, 2015)
Multiple requests among the same browser session are counted as one view.
If you mouse over a chart, the values of data points will be shown.


Cite this article

[IEEE Style]
Y. Zeng and T. M. Chen, "Classification of Traffic Flows into QoS Classes by Unsupervised Learning and KNN Clustering," KSII Transactions on Internet and Information Systems, vol. 3, no. 2, pp. 134-146, 2009. DOI: 10.3837/tiis.2009.02.001.

[ACM Style]
Yi Zeng and Thomas M. Chen. 2009. Classification of Traffic Flows into QoS Classes by Unsupervised Learning and KNN Clustering. KSII Transactions on Internet and Information Systems, 3, 2, (2009), 134-146. DOI: 10.3837/tiis.2009.02.001.

[BibTeX Style]
@article{tiis:19810, title="Classification of Traffic Flows into QoS Classes by Unsupervised Learning and KNN Clustering", author="Yi Zeng and Thomas M. Chen and ", journal="KSII Transactions on Internet and Information Systems", DOI={10.3837/tiis.2009.02.001}, volume={3}, number={2}, year="2009", month={April}, pages={134-146}}