Facing Fault Management as It Is, Aiming for What You Would Like It to Be

Research output: Chapter in Book/Report/Conference proceedingConference contribution

9 Citations (Scopus)

Abstract

Telecommunication systems are built with extensive redundancy and complexity to ensure robustness and quality of service. Such systems requires complex fault identification and management tools. Fault identification and management are generally handled by reducing the number of alarm events (symptoms) presented to the operating engineer through monitoring, filtering and masking. The goal is to determine and present the actual underlying fault. Fault management is a complex task, subject to uncertainty in the symptoms presented. In this paper two key fault management approaches are considered: (i) rule discovery to attempt to present fewer symptoms with greater diagnostic assistance for the more traditional rule based system approach and (ii) the induction of Bayesian Belief Networks (BBNs) for a complete "intelligent" approach. The paper concludes that the research and development of the two target fault management systems can be complementary.
LanguageEnglish
Title of host publicationUnknown Host Publication
Place of PublicationBerlin
Pages31-45
Number of pages15
DOIs
Publication statusPublished - Apr 2002
EventSoft-ware 2002: Computing in an Imperfect World - Belfast, Northern Ireland
Duration: 1 Apr 2002 → …

Conference

ConferenceSoft-ware 2002: Computing in an Imperfect World
Period1/04/02 → …

Fingerprint

Telecommunication systems
Knowledge based systems
Bayesian networks
Redundancy
Quality of service
Engineers
Monitoring
Uncertainty

Cite this

@inproceedings{6d71f10d176f4ae88b68312c7017ae98,
title = "Facing Fault Management as It Is, Aiming for What You Would Like It to Be",
abstract = "Telecommunication systems are built with extensive redundancy and complexity to ensure robustness and quality of service. Such systems requires complex fault identification and management tools. Fault identification and management are generally handled by reducing the number of alarm events (symptoms) presented to the operating engineer through monitoring, filtering and masking. The goal is to determine and present the actual underlying fault. Fault management is a complex task, subject to uncertainty in the symptoms presented. In this paper two key fault management approaches are considered: (i) rule discovery to attempt to present fewer symptoms with greater diagnostic assistance for the more traditional rule based system approach and (ii) the induction of Bayesian Belief Networks (BBNs) for a complete {"}intelligent{"} approach. The paper concludes that the research and development of the two target fault management systems can be complementary.",
author = "R Sterritt",
year = "2002",
month = "4",
doi = "10.1007/3-540-46019-5_3",
language = "English",
isbn = "3-540-43481-X",
pages = "31--45",
booktitle = "Unknown Host Publication",

}

Sterritt, R 2002, Facing Fault Management as It Is, Aiming for What You Would Like It to Be. in Unknown Host Publication. Berlin, pp. 31-45, Soft-ware 2002: Computing in an Imperfect World, 1/04/02. https://doi.org/10.1007/3-540-46019-5_3

Facing Fault Management as It Is, Aiming for What You Would Like It to Be. / Sterritt, R.

Unknown Host Publication. Berlin, 2002. p. 31-45.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Facing Fault Management as It Is, Aiming for What You Would Like It to Be

AU - Sterritt, R

PY - 2002/4

Y1 - 2002/4

N2 - Telecommunication systems are built with extensive redundancy and complexity to ensure robustness and quality of service. Such systems requires complex fault identification and management tools. Fault identification and management are generally handled by reducing the number of alarm events (symptoms) presented to the operating engineer through monitoring, filtering and masking. The goal is to determine and present the actual underlying fault. Fault management is a complex task, subject to uncertainty in the symptoms presented. In this paper two key fault management approaches are considered: (i) rule discovery to attempt to present fewer symptoms with greater diagnostic assistance for the more traditional rule based system approach and (ii) the induction of Bayesian Belief Networks (BBNs) for a complete "intelligent" approach. The paper concludes that the research and development of the two target fault management systems can be complementary.

AB - Telecommunication systems are built with extensive redundancy and complexity to ensure robustness and quality of service. Such systems requires complex fault identification and management tools. Fault identification and management are generally handled by reducing the number of alarm events (symptoms) presented to the operating engineer through monitoring, filtering and masking. The goal is to determine and present the actual underlying fault. Fault management is a complex task, subject to uncertainty in the symptoms presented. In this paper two key fault management approaches are considered: (i) rule discovery to attempt to present fewer symptoms with greater diagnostic assistance for the more traditional rule based system approach and (ii) the induction of Bayesian Belief Networks (BBNs) for a complete "intelligent" approach. The paper concludes that the research and development of the two target fault management systems can be complementary.

UR - http://link.springer.de/link/service/series/0558/tocs/t2311.htm

UR - http://link.springer.de/link/service/series/0558/tocs/t2311.htm

U2 - 10.1007/3-540-46019-5_3

DO - 10.1007/3-540-46019-5_3

M3 - Conference contribution

SN - 3-540-43481-X

SP - 31

EP - 45

BT - Unknown Host Publication

CY - Berlin

ER -