Presentation 2008-11-13
Decomposition of Network Traffic in the Internet Exchange Point (JP-IX) by a state space model
Takayuki MIYAJIMA, Kazuo YANA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) This paper describes a statistical method to decompose network traffic time series into several characteristic variations. A state space model is constructed assuming that the network traffic consists of 1) trend, 2) periodic, 3) stationary AR, 4) holiday adjustment and 5) random components. The Maximum likelihood method is applied to estimate model parameters. As an illustrative example, the method is applied to the data observed at JPIX (Japan Internet Exchange) which reflects the overall backbone network traffic in Japan. The application showed the method is useful for quantitative characterization of the network traffic time series.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) State Space Model / Decomposition / Network Traffic / Kalman Filter / JPIX
Paper # NS2008-91
Date of Issue

Conference Information
Committee NS
Conference Date 2008/11/6(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 Network Systems(NS)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Decomposition of Network Traffic in the Internet Exchange Point (JP-IX) by a state space model
Sub Title (in English)
Keyword(1) State Space Model
Keyword(2) Decomposition
Keyword(3) Network Traffic
Keyword(4) Kalman Filter
Keyword(5) JPIX
1st Author's Name Takayuki MIYAJIMA
1st Author's Affiliation College of Engineering, Hosei University()
2nd Author's Name Kazuo YANA
2nd Author's Affiliation College of Engineering, Hosei University
Date 2008-11-13
Paper # NS2008-91
Volume (vol) vol.108
Number (no) 286
Page pp.pp.-
#Pages 5
Date of Issue