Graduate School and Research Center in Digital Sciences

Cloud-based content distribution on a budget

Albanese, Francesco; Carra, Damiano; Michiardi, Pietro ; Bestavros, Azer

Computer Science Technical Report BUCS-TR-2010-022

swarm-to-cloud interactions,   CYCLOPS - dynamically adjusts the off-cloudCYCLOPS in a variety bandwidth consumed by content servers (which represents the bulk of the provider's cost) to feed a set of swarming clients, based on a feedback signal that gauges the real-time health of the swarm. Our extensive evaluation of of settings - including controlled PlanetLab and live Internet experiments involving thousands of users - show significant reduction in content distribution costs (by as much as two orders of magnitude) when compared to non-feedback-based swarming solutions, with minor impact on content delivery times.   To leverage the elastic nature of cloud computing, a solution provider must be able to accurately gauge demand for its offering. For applications that involve gauging such demand is not straightforward. In this paper, we propose a general framework, analyze a mathematical model, and present a prototype implementation of a canonical swarmto- cloud application, namely peer-assisted content delivery. Our system - called    

Document Bibtex

Title:Cloud-based content distribution on a budget
Department:Data Science
Eurecom ref:3223
Bibtex: @techreport{EURECOM+3223, year = {2010}, title = {{C}loud-based content distribution on a budget}, author = {{A}lbanese, {F}rancesco and {C}arra, {D}amiano and {M}ichiardi, {P}ietro and {B}estavros, {A}zer}, number = {EURECOM+3223}, month = {08}, institution = {Eurecom}, url = {},, }
See also: