Presentation 2018-12-25
Network traffic prediction method considering chaos theory with TCP and UDP
Naoto Suzuki, Sumiko Miyata,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) With the diversification of streaming communication, we need to predict network traffic in a mixed environment of TCP and UDP. Therefore, various schemes for predicting streaming traffic flowing over a network have been proposed. However, these methods can only be applied to steady state traffic, and take much time to predict the traffic. On the other hand, since it is reported that the amount of Internet traffic always fluctuates greatly, the prediction should be made as shortly as possible. In this paper, it is pointed out that self-similarity which is characteristic of chaos can be seen in network traffic. Moreover, we show that network traffic can be predicted in the short term by using deterministic nonlinear nature. In addition, simulation is performed by using model for 30 client terminals and servers. We show that traffic data occurs chaos. Moreover, we show the effectiveness of this method by using proposed traffic prediction.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Chaos Theory / Local Reconstruction / Traffic Prediction / Attractor
Paper # MoNA2018-43
Date of Issue 2018-12-18 (MoNA)

Conference Information
Committee MoNA
Conference Date 2018/12/25(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English) General
Chair Ryoichi Shinkuma(Kyoto Univ.)
Vice Chair Shigeaki Tagashira(Kansai Univ.) / Gen Kitagata(Tohoku Univ.)
Secretary Shigeaki Tagashira(Kyushu Univ.) / Gen Kitagata(NEC)
Assistant Ken Usui(KDDI Research) / Kenji Kanai(Waseda Univ.)

Paper Information
Registration To Technical Committee on Mobile Network and Applications
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Network traffic prediction method considering chaos theory with TCP and UDP
Sub Title (in English)
Keyword(1) Chaos Theory
Keyword(2) Local Reconstruction
Keyword(3) Traffic Prediction
Keyword(4) Attractor
1st Author's Name Naoto Suzuki
1st Author's Affiliation Shibaura Institute of Technology(SIT)
2nd Author's Name Sumiko Miyata
2nd Author's Affiliation Shibaura Institute of Technology(SIT)
Date 2018-12-25
Paper # MoNA2018-43
Volume (vol) vol.118
Number (no) MoNA-378
Page pp.pp.25-30(MoNA),
#Pages 6
Date of Issue 2018-12-18 (MoNA)