No abstract

As a popular means for capturing behavioural requirements, 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 previous work we presented an automated approach for predicting software system reliability that extends a scenario specification to model (1) the probability of component failure, and (2) scenario transition probabilities. Probabilistic behaviour models of the system are then synthesized from the extended scenario specification. From the system behaviour model, reliability prediction can be computed. This paper complements our previous work and presents a sensitivity analysis that supports reasoning about how component reliability and usage profiles impact on the overall system reliability. For this purpose, we present how the system reliability varies as a function of the components reliabilities and the scenario transition probabilities. Taking into account the concurrent nature of component-based software systems, we also analyse the effect of implied scenarios prevention into the sensitivity analysis of our reliability prediction technique.