Home // CLOUD COMPUTING 2016, The Seventh International Conference on Cloud Computing, GRIDs, and Virtualization // View article

Online Traffic Classification Based on Swarm Intelligence

Authors:
Takumi Sue
Yuichi Ohsita
Masayuki Murata

Keywords: Traffic Classification; Hierarchical Clustering; Swarm Intelligence

Abstract:
In this paper, we propose a new traffic classification method which constructs hierarchical clusters using the statistics of uncompleted flows. By constructing the hierarchical groups, we can identify the similarity of the groups. If flows of a new application construct a new group in the lower layer, but they are classified in an existing group in the upper layer, the manager can estimate the characteristic of the new application from the characteristic of the existing group. In our method, the hierarchical groups are constructed based on the clustering method called AntTree; the each flow moves over the tree and find the nodes whose similarity to the nodes exceeds the threshold. By setting the threshold based on the number of monitored packets of the flow, we classify the flow if the statistics of the flow become sufficiently accurate. Otherwise we wait another packets that improve the accuracy of the statistics.

Pages: 131 to 138

Copyright: Copyright (c) IARIA, 2016

Publication date: March 20, 2016

Published in: conference

ISSN: 2308-4294

ISBN: 978-1-61208-460-2

Location: Rome, Italy

Dates: from March 20, 2016 to March 24, 2016