Distributed architectures for surrogate clustering in CDNs: a simulation-based analysis

Content distribution networks (CDNs) are the most adopted solution for an efficient content delivery over the Internet. They are usually based on caching content, originally produced and stored in origin servers, into surrogate servers which are closer to final users so as to improve the average user perceived latency related to content requests. To further improve the performance of CDNs, new caching techniques should be designed which are not limited to stand-alone surrogate servers but involve coordination among a set of surrogate servers. In this paper we therefore propose the design and evaluation of several distributed architectures for clustering surrogate server: master/slave, multicast-based and peer-to-peer. An agent-oriented modeling and simulation methodology is exploited to model and evaluate the proposed architectures in significant scenarios. The results obtained from simulation show that the designed surrogate clustering architectures allow to improve performance with respect to caching techniques of conventional CDNs. Copyright 2009 ACM.