An Approach for Self-Reconfiguring and Fault-Tolerant Distributed Real-Time Systems

In this paper we present an approach for the self reconfiguration of distributed micro-controllers for increased fault tolerance. Based on a modified distributed system topology utilizing a time division multiple access (TDMA) protocol, i.e., Flex Ray, we present a self-organized distributed coordinator concept which performs the self-reconfiguration in the case of node failures. We introduce a distributed coordinator, which utilizes redundant slots in the Flex Ray communication schedule and combines messages in configured protocol frames and slots to avoid a complete bus restart. As such, the self-reconfiguration is realized by means of predetermined information about resulting changes in the communication dependencies and (re-)assignments determined in the design phase. To retrieve the necessary information, we present an analytical approach, which determines a combined solution for the initial configuration and all possible reconfigurations for the remaining nodes of the Flex Ray network in case of node failures. Hence, through this method we can design self-reconfiguring network-based systems enabling the handling of node failures for an increased fault tolerance.