Presentation 2013-05-17
System Identification of Network Service Processing Time with Genetic Programming
Ryuichi HAYASHIDA, Kohei WATABE, Hiroyuki OHSAKI,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) In this paper, we investigate experimentally how accurately the dynamics of processing time of network service is modeled with Genetic Programming (GP), one of black box modeling approaches. Generally, network services are provided on a system that consists of several elements like computers (servers and clients), storages, routers, and links. As computers and network virtualization technology become widespread, it gets more difficult to build a model of the entire system by modeling individual elements of the system and combining them (white box modeling). On the other hand, huge amount of network/server logs are collected at the edge of the network or server because of increasing processing speed of hardware and software, and decreasing the cost of storage. In this paper, we investigate how accurately characteristics of the network service is modeled using huge amount of log information collected at the edge of network and server. By analyzing the fitness of the model when traffic rate, the measurement period of logs and parameters of GP are changed, we clarify feasibility of network services processing time modeling with GP.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Genetic Programming / Black Box Modeling / System Identification / Network Service
Paper # IN2013-21
Date of Issue

Conference Information
Committee IN
Conference Date 2013/5/9(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) System Identification of Network Service Processing Time with Genetic Programming
Sub Title (in English)
Keyword(1) Genetic Programming
Keyword(2) Black Box Modeling
Keyword(3) System Identification
Keyword(4) Network Service
1st Author's Name Ryuichi HAYASHIDA
1st Author's Affiliation Graduate School of Information Science and Technology, Osaka University()
2nd Author's Name Kohei WATABE
2nd Author's Affiliation Graduate School of Information Science and Technology, Osaka University
3rd Author's Name Hiroyuki OHSAKI
3rd Author's Affiliation Department of Informatics School of Science and Technology, Kwansei Gakuin University
Date 2013-05-17
Paper # IN2013-21
Volume (vol) vol.113
Number (no) 36
Page pp.pp.-
#Pages 6
Date of Issue