Dependability analysis of distributed computing systems using stochastic Petri nets

Models based on stochastic Petri nets are developed to estimate the reliability/availability of distributed systems. The modeling approach discussed combines stochastic Petri net modeling and previous reliability algorithms so that not only can failures of nodes and links be modeled, but also the effect of global repairs can be considered. The models can be used to derive estimations on the successful execution of one or more programs distributed in the system. In a distributed computing environment successful execution means that all distributed programs can access all the required remote files even in the presence of faults. A global repair model for a small system is considered in detail. A generalization and the results reported for complex systems were obtained by using the Stochastic Petri Net Package (SPNP).<
>