Synchronous Concurrent Broadcasts for Intermittent Channels with Bounded Capacities

Abstract: In this work we extend the recently proposed synchronous broadcast algorithm amnesiac flooding to the case of intermittent communication channels. In amnesiac flooding a node forwards a received message in the subsequent round. There are several reasons that render an immediate forward of a message impossible: Higher priority traffic, overloaded channels, etc. We show that postponing the forwarding for one or more rounds prevents termination. Our extension overcomes this shortcoming while retaining the advantages of the algorithm: Nodes don't need to memorize the reception of a message to guarantee termination and messages are sent at most twice per edge. This extension allows to solve more general broadcast tasks such as multi-source broadcasts and concurrent broadcasts for systems with bounded channel capacities.