A neural network for diagnosing multiprocessor and multicomputer systems

Abstract

Purpose – The purpose of this paper is to describe a novel diagnosis approach, using neural networks (NNs), which can be used to identify faulty nodes in distributed and multiprocessor systems.

Design/methodology/approach – Based on a literature‐based study focusing on research methodology and theoretical frameworks, the conduct of an ethnographic case study is described in detail. A discussion of the reporting and analysis of the data is also included.

Findings – This work shows that NNs can be used to implement a more efficient and adaptable approach for diagnosing faulty nodes in distributed systems. Simulations results indicate that the perceptron‐based diagnosis is a viable addition to present diagnosis problems.

Research limitations/implications – This paper presents a solution for the asymmetric comparison model. For a more generalized approach that can be used for other comparison or invalidation models this approach requires a multilayer neural network.

Practical implications – The extensive simulations conducted clearly showed that the perceptron‐based diagnosis algorithm correctly identified all the millions of faulty situations tested. In addition, the perceptron‐based diagnosis requires an off‐line learning phase which does not have an impact on the diagnosis latency. This means that a fault set can be easily and rapidly identified. Simulations results showed that only few milliseconds are required to diagnose a system, hence, one can start talking about “real‐time” diagnosis.