Utilizing Hidden Markov Models for Formal Reliability Analysis of Real-Time Communication Systems with Errors

In the near future embedded systems will be faced with the phenomena of increasing error rates, caused by a variety of error sources that have to be considered during the design process. In this paper we propose a method to derive the reliability of a real-time capable CAN bus system with errors. Individual errors on the CAN bus might be correlated in arbitrary way; the proposed algorithm will cover this. It is based on a previous work on reliability analysis that has been restricted to uncorrelated bit errors. To extend this approach we first introduce a suitable error model to describe arbitrary correlations between bit errors. As a key novelty we present an extended analysis procedure that takes this error model into account. This new approach will be utilized to determine the effects of burst errors and to demonstrate the necessity of appropriate error models for reliability analysis.