Modelling Predictable Component-Based Distributed Control Architectures

Current models of component architectures require extensions to support compositional reasoning about extra-functional properties such as worst-case time. Studying such properties in architectures is complicated since actual components may not yet be chosen during architectural design, and different choices may have significant and hard to predict effects on the system properties. In this paper we show how finite state automata and Petri nets may be extended to provide compositionality of extra-functional properties. We focus on worst-case time and safety. We illustrate the use of these techniques on the well-known production cell case study. In collaboration with industry we are currently applying a prototype analysis system for predicting critical properties of real-time industrial control systems.