Replica placement in adaptive content distribution networks

Abstract

Adaptive content networking is a promising new approach aimed at scalable delivery of content to a pervasive client population. By adaptive content delivery networks (A-CDN) content is adapted, replicated and delivered to the clients in a cost-quality-optimized fashion. The integration of content adaptation into CDNs minimizes the interference of adaptation with replication effectiveness.The paper presents ongoing research on replica placement in A-CDNs. Based on a static model for cost-quality-optimized adaptive content networking, algorithms to optimize the placement of replicas in the surrogates of an A-CDN are discussed. The dynamics of a real Web scenario are not explicitly taken into account by the algorithms. Whereas long-term dynamics are dealt with by periodic adjustments of the underlying model and recalculation of an optimal placement, short term dynamics are considered to result in inaccuracies in the system and load model. Therefore, algorithms being tolerant to an imperfect underlying model are chosen.As adaptation path composition turns out to be a subproblem of replica placement in A-CDNs, we also introduce an algorithm for optimal adaptation path composition.