Presentation 2014-11-19
Proposal of Periodicity Detection Method for Separation of Background Traffic
MINH Quang TRAN, Hideyuki KOTO, Shigehiro ANO, Lu CHEN, Shin'ichi ARAKAWA, Masayuki MURATA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Background (BG) and foreground (FG) network traffic separation is one of the essential tasks in network traffic analysis and management used by network carriers to assure QoS and QoE. Periodicity is one of the natures of BG traffic, thus it can be leveraged to effectively differentiate BG from FG traffic. This paper proposes a novel approach, namely the Period Candidate Array (PCA), to detect traffic flow periodicity targeting BG/FG traffic separation. The PCA extracts only necessary information from long but sparse traffic data thus decreases the computational space. The proposed approach significantly reduces the complexity from 0(n log n), as known in the conventional approaches, to 0(n). In addition, the proposed method can be applied to traffic affected by network delays. Experimental evaluations reveal the effectiveness and efficiency of our proposed approach.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Background/foreground traffic separation / traffic flows / periodicity / period candidate / extended period
Paper # MoNA2014-55
Date of Issue

Conference Information
Committee MoNA
Conference Date 2014/11/11(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Mobile Network and Applications(MoNA)
Language ENG
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Proposal of Periodicity Detection Method for Separation of Background Traffic
Sub Title (in English)
Keyword(1) Background/foreground traffic separation
Keyword(2) traffic flows
Keyword(3) periodicity
Keyword(4) period candidate
Keyword(5) extended period
1st Author's Name MINH Quang TRAN
1st Author's Affiliation KDDI R&D Laboratories, Inc.()
2nd Author's Name Hideyuki KOTO
2nd Author's Affiliation KDDI R&D Laboratories, Inc.
3rd Author's Name Shigehiro ANO
3rd Author's Affiliation KDDI R&D Laboratories, Inc.
4th Author's Name Lu CHEN
4th Author's Affiliation Department of Information Science, Osaka University
5th Author's Name Shin'ichi ARAKAWA
5th Author's Affiliation Department of Information Science, Osaka University
6th Author's Name Masayuki MURATA
6th Author's Affiliation Department of Information Science, Osaka University
Date 2014-11-19
Paper # MoNA2014-55
Volume (vol) vol.114
Number (no) 308
Page pp.pp.-
#Pages 6
Date of Issue