Presentation 2010-09-02
Network Traffic Estimation with Dynamic Model Selection Approach
Kousuke NOGAMI, Hiroshi YOSHIDA, Kozo SATODA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) In best effort networks, it is necessary to model network behavior properly including network delay and packet loss in order to stabilize quality of delivering audio/video content. On the other hand, it's said that network has two features, long-range-dependency and phase transition, then this paper proposes a modeling approach to reflect these features. In this approach, network behavior is learned by multiple hidden Markov models in parallel and the proper model is selected among them based on current network behavior. The result of simulation shows that this approach can describe above two network features.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Network Modeling / Dynamic Model Selection / Hidden Markov Model
Paper # IN2010-53
Date of Issue

Conference Information
Committee IN
Conference Date 2010/8/26(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 Information Networks (IN)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Network Traffic Estimation with Dynamic Model Selection Approach
Sub Title (in English)
Keyword(1) Network Modeling
Keyword(2) Dynamic Model Selection
Keyword(3) Hidden Markov Model
1st Author's Name Kousuke NOGAMI
1st Author's Affiliation Service Platforms Research Laboratories, NEC()
2nd Author's Name Hiroshi YOSHIDA
2nd Author's Affiliation Service Platforms Research Laboratories, NEC
3rd Author's Name Kozo SATODA
3rd Author's Affiliation Service Platforms Research Laboratories, NEC
Date 2010-09-02
Paper # IN2010-53
Volume (vol) vol.110
Number (no) 191
Page pp.pp.-
#Pages 6
Date of Issue