The Internet Traffic Classification Method Using LPC Cepstrum

Masatsugu ICHINO  Hiroaki MAEDA  Naohisa KOMATSU  Kei TAKESHITA  Masayuki TSUJINO  Haruhisa HASEGAWA  Hideaki YOSHINO 

Publication
B - Abstracts of IEICE TRANSACTIONS on Communications (Japanese Edition)  Vol.J95-B  No.7  pp.835-847
Publication Date: 2012/07/01
Online ISSN: 1881-0209
Print ISSN: 1344-4697
Type of Manuscript: Special Section PAPER (Special Section on Frontiers by Young Researchers)
Category: 
Keyword: 
traffic,  QoS,  service classification,  classifier,  LPC cepstrum, 

Full Text(in Japanese): PDF(836.6KB)

Summary: 
The volume of the internet traffic is increasing rapidly beause of the spread of the broadband access and the increase in internet backbone capacities. Also, the volume of each appliation varies widely. In this situation, it is important to understand which application should to be monitored. However, monitoring traffic for each application is difficult because of the load of network elements. In this paper, we propose an application traffic classification method considering time series of the traffic by using LPC cepstrum. We explain the whole system and show the efficiency of our method by comparing with the existing methods.