Investigating Temporal Patterns of Fault Behaviour within Large Telephony Networks

  • Authors:
  • Dave Yearling;David J. Hand

  • Affiliations:
  • -;-

  • Venue:
  • IDA '01 Proceedings of the 4th International Conference on Advances in Intelligent Data Analysis
  • Year:
  • 2001

Quantified Score

Hi-index 0.00

Visualization

Abstract

This paper outlines a first pass technique that can be used to pin point non-maintainable plant in large telephony networks for further investigation. Due to their size, complexity and low fault count, recognising rogue plant in these copper wire networks can be very difficult. By just concentrating on their respective fault time series, we may characterise plant items using a combined approach based on SQL and renewal theory. SQL provides a pre-analysis filter and renewal theory differentiates plant in terms of their respective hazard functions. From this we can form interpretations of plant maintainability.