A multiple segmented backups scheme for dependable real-time communication in multihop networks

Abstract

Several distributed real-time applications require fault-tolerance apart from guaranteed timeliness at acceptable levels of overhead. It is essential to provide them with hard guarantees on recovery delays due to component-failures, which cannot be ensured in traditional datagram services. The application of computer networks have expanded to areas in which communication services are considered critical and the failure of which may lead to mission threatening scenarios. These critical communication services need to survive multiple, simultaneous component faults that can occur in the network, due to various reasons. Several schemes exist which attempt to guarantee recovery in a timely and resource efficient manner from such multiple faults. These methods center around apriori reservation of network resources called spare resources along backup channels, in addition to each primary channel. These backup channels (end-to-end backup) are usually routed from the source to the destination along a path disjoint with the primary. If a primary channel fails, one of the backups can be activated, and this makes the realtime connection dependable. In this paper, we propose a new method of multiple segmented backups for dependable communication in multihop networks, which improves upon existing methods. Various scenarios in multihop networks (including the current Internet) where our scheme can be implemented are also discussed. Finally, we demonstrate the superiority of our method by presentation of the results of our simulation studies.