Using Scenarios to Predict the Reliability of Concurrent Component-Based Software Systems

Abstract

Scenarios are a popular means for capturing behavioural requirements of software systems early in the lifecycle. Scenarios show how components interact to provide system level functionality. If component reliability information is available, scenarios can be used to perform early system reliability assessment. In this paper we present a novel automated approach for predicting software system reliability. The approach involves extending a scenario specification to model (1) the probability of component failure, and (2) scenario transition probabilities derived from an operational profile of the system. From the extended scenario specification, probabilistic behaviour models are synthesized for each component and are then composed in parallel into a model for the system. Finally, a user-oriented reliability model described by Cheung is used to compute a reliability prediction from the system behaviour model. The contribution of this paper is a reliability prediction technique that takes into account the component structure exhibited in the scenarios and the concurrent nature of component-based systems. We also show how implied scenarios induced by the component structure and system behaviour described in the scenarios can be used to evolve the reliability prediction.