Caching neighborhood protocol: A foundation for building dynamic Web caching hierarchies with proxy servers

In this paper we propose a Caching Neighborhood Protocol (CNP) that describes an infrastructure upon which proxy servers can build dynamic Web caching hierarchies. Such a scheme decreases the response times for the requests by increasing the availability of documents without compromising the currency of the rendered documents. Some qualitative reasonings and studies on the request accessing traces collected by a proxy server at NLANR are presented to justify CNP. A five-day trace analysis shows that the top 20% Web sites (in terms of frequency of accesses) provide 93% of the most frequently accessed top 20% documents and such top 20% documents account for 94% of the documents that have been accessed more than once. Hence, an important observation is that caching the most popular documents provided by the most popular Web sites would be a very effective approach for Web caching