Improving Web Access Efficiency Using P2P Proxies

摘要

Recent studies have shown that caching data at the proxy server can improve the user response time for web document retrieval. However, a single cache proxy has a limited cache space, thus the amount of data that can be cached is limited. In this paper, we organize the distributed proxy servers into a group of peer-to-peer cache proxies. By exploiting the aggregate cache space and computing power, we can reduce the average user response time and improve our quality of services. Unlike some previous works that achieve the similar results by replacing the single proxy server with a cluster of servers, we simply link the existing distributed proxy servers using a set of rules for connection, data cache and data routing to build a self-organized scalable distributed P2P proxy caching system. Our simulation has proven the feasibility and effectiveness of our cache system. In addition, our P2P proxy cache system is configured using individual based model and is easy to implement in a large scale distributed environment.