Alarm correlation and network fault resolution using the Kohonen self-organising map

Abstract

A vital role for a large telecommunications operator is the ability to effectively manage its network. With increasing system size, complexity and bandwidth threatening to overload current management systems, it is no surprise that network management is a high priority for leading telecommunications providers. In this paper, a novel approach to fault management is investigated in which the advantages of artificial neural network technologies are used to complement and extend the capability of traditional systems. In particular, it is shown how a system based on Kohonen (1990) self-organising map theory can be successfully implemented as a means of identifying fault scenarios arising in an SDH-based environment.