Using k-nearest neighbor method to identify poison message failure

Research output: Contribution to conferencePaperpeer-review

Abstract

Poison message failure is a mechanism that has been responsible for large scale failures in both telecommunications and IP networks. The poison message failure can propagate in the network and cause unstable network In this paper, we apply machine learning, data mining technique in network fault management area. We use k-nearest neighbor method to identify the poison message failure. We also propose a "probabilistic" k-nearest neighbor method which outputs a probability distribution about the poison message. Through extensive simulations, we show that k-nearest neighbor method is very effective in identifying the responsible message type.

Original languageEnglish
Pages2113-2117
Number of pages5
StatePublished - 2004
EventGLOBECOM'04 - IEEE Global Telecommunications Conference - Dallas, TX, United States
Duration: 29 Nov 20043 Dec 2004

Conference

ConferenceGLOBECOM'04 - IEEE Global Telecommunications Conference
Country/TerritoryUnited States
CityDallas, TX
Period29/11/043/12/04

Fingerprint

Dive into the research topics of 'Using k-nearest neighbor method to identify poison message failure'. Together they form a unique fingerprint.

Cite this