Performance and dependability analysis of fault-tolerant networks

Fault-tolerant networks continue their operation even in the presence of some failures. However, failures of components or subsystems can considerably affect the performance behaviour. This paper illustrates the use of Stochastic Reward Models (SRMs) for evaluating combined performance and dependability of fault-tolerant networks. A SRM is composed of a stochastic process, describing the evolution of the system, and a superimposed reward structure, reflecting different performance levels. To study the overall network behaviour, different network performance/dependability are introduced and discussed. Due to the arising complexity of exact SRMs a complexity reduction approach is proposed. For highly reliable networks an approximation of the model is presented.