Gossip-Based Counting in Dynamic Networks

We propose Gossipico, a gossip algorithm to average, sum or find minima and maxima over node values in a large, distributed, and dynamic network. Unlike previous work, Gossipico provides a continuous estimate of, for example, the number of nodes, even when the network becomes disconnected. Gossipico converges quickly due to the introduction of a beacon mechanism that directs messages to an autonomously selected beacon node. The information spread through the network shows a percolation-like phase-transition and allows information to propagate along near-shortest paths. Simulations in various different network topologies (ranging in size up to one million nodes) illustrate Gossipico's robustness against network changes and display a near-optimal count time. Moreover, in a comparison with other related gossip algorithms, Gossipico displays an improved and more stable performance over various classes of networks.