Distributed council election

This paper studies the problem of electing a small number of representatives (council) out of a (possible large) group of anonymous candidates. The problem arises in scenarios such as multicast where, to avoid feedback implosion, a small subset of the receivers is chosen to provide feedback on network conditions. We present several algorithms for this problem and analyze the expected number of messages and rounds required for their convergence. In particular, we present an algorithm that almost always converges in one round using a small number of messages (for typical council size) when the number of hosts is known. In the case where the number of hosts is unknown (and too large to be polled), our algorithms converge in a small number of rounds that improves previous results by Bolot et al. (1994).