Dynamic Reconfiguration of FlexRay Schedules for Response Time Reduction in Asynchronous Fault-Tolerant Networks

In this paper, we present fault-tolerance strategies for implementing passive replication techniques in networked embedded systems based on TDMA-communication such as FlexRay busses. In particular, we assume that processes are replicated at different nodes for tolerating node failures. Hence, if one node fails another node can execute the process and requires the bandwidth for transmitting those messages created by the process over the bus medium. Two concepts are introduced to solve this problem: 1.) to replicate not only the processes but also the messages and to reserve the required bandwidth a priori at design time or 2.) to reconfigure the TDMA-schedule and assign the bandwidth dynamically to the nodes. Obviously, reserving bandwidth for each failure case might lead to a huge overhead and to long response times. Therefore, we provide different reconfiguration strategies for the recently developed FlexRay bus. Moreover, the timing behavior as well as the implementation overhead are evaluated with the help of an experimental setup consisting of five FlexRay nodes.