Presentation 2011-01-17
Proposal and Preliminary Evaluation of System Diagnosis Technique for Large-scale Computer Network by Using Bayesian Network
Shingo HARASHIMA, Hitoshi YABUSAKI, Wataru SAKAMOTO, Hiroaki NISHI,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) For the past network which had comparatively low speed links and simple structure, we could identify the cause of system failure by checking every network device and link. However, it is difficult to find the failure in complicated network, since checking every device and link takes a lot of cost. Therefore, the detection method of the failure from less information is required. This report proposes the system diagnosis technique that estimates congestion probability from the information of bursty traffic by using Bayesian Network. In addition, simulation results in large-scale computer network are shown. The technique predicted all link congestion under the same condition as the learning data. However, it didn't predict link congestion under the different condition from the learning data. In case of a unpredicted condition, the prediction of congestion can be achieved by using the independence of the occurrence probability of burst.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Network Management System / Bayesian Network
Paper # VLD2010-86,CPSY2010-41,RECONF2010-55
Date of Issue

Conference Information
Committee RECONF
Conference Date 2011/1/10(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 Reconfigurable Systems (RECONF)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Proposal and Preliminary Evaluation of System Diagnosis Technique for Large-scale Computer Network by Using Bayesian Network
Sub Title (in English)
Keyword(1) Network Management System
Keyword(2) Bayesian Network
1st Author's Name Shingo HARASHIMA
1st Author's Affiliation Graduate School of Science and Technology, Keio University()
2nd Author's Name Hitoshi YABUSAKI
2nd Author's Affiliation Central Research Laboratory, Hitachi, Ltd.
3rd Author's Name Wataru SAKAMOTO
3rd Author's Affiliation Graduate School of Engineering Science, Osaka University
4th Author's Name Hiroaki NISHI
4th Author's Affiliation Graduate School of Science and Technology, Keio University
Date 2011-01-17
Paper # VLD2010-86,CPSY2010-41,RECONF2010-55
Volume (vol) vol.110
Number (no) 362
Page pp.pp.-
#Pages 6
Date of Issue