Using neural networks to identify control and management plane poison messages

Xiaojiang Du, Mark A. Shayman, Ronald Skoog

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

2 Scopus citations

Abstract

Poison message failure propagation is a mechanism that has been responsible for large scale failures in both telecommunications and IP networks: Some or all of the network elements have a software or protocol 'bug' that is activated on receipt of a certain network control/management message (the poison message). This activated 'bug' will cause the node to fail with some probability. If the network control or management is such that this message is persistently passed among the network nodes, and if the node failure probability is sufficiently high, large-scale instability can result. Identifying the responsible message type can permit filters to be configured to block poison message propagation, thereby preventing instability. Since message types have distinctive modes of propagation, the node failure pattern can provide valuable information to help identify the CUlprit message type. Through extensive simulations, we show that artificial neural networks are effective in isolating the responsible message type.

Original languageEnglish
Title of host publicationIntegrated Network Management VIII
Subtitle of host publicationManaging It All - IFIP/IEEE 8th International Symposium on Integrated Network Management, IM 2003
Pages621-634
Number of pages14
DOIs
StatePublished - 2003
EventIFIP/IEEE 8th International Symposium on Integrated Network Management, IM 2003 - Colorado Springs, CO, United States
Duration: 24 Mar 200328 Mar 2003

Publication series

NameIFIP Advances in Information and Communication Technology
Volume118
ISSN (Print)1868-4238

Conference

ConferenceIFIP/IEEE 8th International Symposium on Integrated Network Management, IM 2003
Country/TerritoryUnited States
CityColorado Springs, CO
Period24/03/0328/03/03

Keywords

  • Fault management
  • Neural network
  • Node failure pattern
  • Poison message

Fingerprint

Dive into the research topics of 'Using neural networks to identify control and management plane poison messages'. Together they form a unique fingerprint.

Cite this