Assessment of performance and dependability in embedded control systems: methodology and case study.

Distributed and embedded control systems play an increasing role in modern safety-critical systems, and there is a pressing need to investigate the impact of different design decisions on system performance and safety integrity. In this paper, a methodology for the measurement and estimation of such attributes is presented. The methodology integrates statistical fault-injection testing with the application of on-line, model-based performance monitoring of the embedded control system under test. The methodology is particularly suited to late-phase system testing in which "hardwarein- the-loop" (HIL) simulation techniques are employed. The methodology is illustrated in an extended case study, in which the performance and dependability of eight possible designs for an automotive control system are compared. It is concluded that the methodology is a useful adjunct to the available testing and analysis techniques for such systems.