Formalizing Compute-Aggregate Problems in Cloud Computing

Abstract

Efficient representation of data aggregations is a fundamental problem in modern big data applications, where network topologies and deployed routing and transport mechanisms play a fundamental role to optimize desired objectives: cost, latency, and others. We study the design principles of routing and transport infrastructure and identify extra information that can be used to improve implementations of computeaggregate tasks. We build a taxonomy of compute-aggregate services unifying aggregation design principles, propose algorithms for each class, analyze them, and support our results with an extensive experimental study.