Fast restoration of real-time communication service from component failures in multi-hop networks

For many applications it is important to provide communication services with guaranteed timeliness and fault-tolerance at an acceptable level of overhead. In this paper, we present a scheme for restoring real-time channels, each with guaranteed timeliness, from component failures in multi-hop networks. To ensure fast/guaranteed recovery, backup channels are set up a priori in addition to each primary channel. That is, a dependable real-time connection consists of a primary channel and one or more backup channels. If a primary channel fails, one of its backup channels is activated to become a new primary channel. We describe a protocol which provides an integrated solution to the failure-recovery problem (i.e., channel switching, resource re-allocation, . . .). We also present a resource sharing method that significantly reduces the overhead of backup channels. The simulation results show that good coverage (in recovering from failures) can be achieved with about 30% degradation in network utilization under a reasonable failure condition. Moreover, the fault-tolerance level of each dependable connection can be controlled, independently of other connections, to reflect its criticality.