Analysis of web-proxy cache replacement algorithms under steady-state conditions

Web-Proxy servers are used to reduce the bandwidth consumption and users' perceived latency while navigating the WWW, by caching the most frequent objects accessed by users. Since they were introduced, most of the evaluations studies related to Web-Proxy caches have focused on the replacement algorithms performance using simulation techniques. But few of them have been done assuring the representativeness of the studies and considering real traces and cache sizes. This paper describes a methodology that permits fair performance comparison studies of replacement algorithms, that is, the system reaches the steady-state and the results are provided showing narrow confidence intervals. An experimental evaluation study applying this methodology is also presented. The study uses a trace-driven simulation framework, real traces containing more than one hundred million of user's requests, and compares three replacement algorithms implemented in actual Web-Proxy caches.