Computational intelligence for distributed fault management in networks using fuzzy cognitive maps

This paper proposes a computationally based expert system for managing fault propagation in internetworks using the concept of fuzzy cognitive maps (FCM), a graphical archetype which encodes and processes vague causal reasoning numerically. The dynamic features of FCM are exploited to characterize the time-varying aspects of network faults, while its graphical features are used as a framework for representing the distributed properties of fault propagation. In this scheme, a network fault due to one or more managed objects induces causal fuzzy relationships on adjacent objects. This causal relationship is captured in a matrix which allows causal inference representations to be viewed as feedback associative memory with computational recall capabilities.