Continuous Gossip-Based Aggregation through Dynamic Information Aging

Abstract

Existing solutions for gossip-based aggregation in peer-to-peer networks use epochs to calculate a global estimation from an initial static set of local values. Once the estimation converges system- wide, a new epoch is started with fresh initial values. Long epochs result in precise estimations based on old measurements and short epochs result in imprecise aggregated estimations. In contrast to this approach, we present in this paper a continuous, epoch-less approach which considers fresh local values in every round of the gossip-based aggregation. By using an approach for dynamic information aging, inaccurate values and values from left peers fade from the aggregation memory. Evaluation shows that the presented approach for continuous information aggregation in peer-to-peer systems monitors the system performance precisely, adapts to changes and is lightweight to operate.