Estimating delay times between cloud datacenters: A pragmatic modeling approach

Abstract

For many applications with inter-datacenter cloud deployments it is important to rely on an accurate model of delay times across different geolocations. Unfortunately, such a model is currently not available to researchers and practitioners. To fill that gap, this letter presents a thorough analysis of real-life latency values collected between different Amazon datacenter locations, and proposes a novel Gaussian mixture approximation model of the round-trip time distribution based on the relaxed boxed approximation algorithm. The proposed model can be effectively used for the emulation/simulation of cross-cloud application and service deployments.