Reliability Evaluation of Broadcast Protocols for FlexRay

Abstract

X-by-wire applications have extremely demanding reliability requirements that are increasingly being addressed through the adoption of distributed and fault-tolerant architectures. The development of these applications is facilitated by the availability of high-level services such as agreement or reliable broadcast (RB). Some dependable communication buses, e.g., TTP-C, already provide these services, whereas FlexRay does not. In this paper, we present an approach to evaluate the reliability of a family of RB protocols implemented both on top of FlexRay and on top of ordinary time-division multiple access (TDMA). In particular, we evaluate the impact of the acknowledgment policy on the reliability of these protocols. We express the reliability as the probability of violation of the agreement and validity properties of the protocol during a mission. For that, we develop an analytical model based on discrete-time Markov chains, which considers a comprehensive set of faults (permanent, transient, omissive, and asymmetric) affecting both nodes and channels, and their effects on the protocol execution. The structure of the model is quite flexible and easily adaptable to other TDMA-based protocols. To assess the sensitivity of the protocol to both internal and external factors, we carried out a large number of experiments considering several network configurations and fault rates. The results show that for FlexRay, the negative-acknowledgment policy provides the same reliability as the positive-acknowledgment policy. However, for TDMA-based protocols that lack FlexRay's ability to distinguish silence from the loss of a message, the negative-acknowledgment policy leads to lower reliability, and its fitness for safety-critical applications depends on the system configuration and environment conditions.