A New Intelligent Predictive Caching Algorithm for Internet Web Servers

Web caching is used to improve the performance of the Internet Web servers. Document caching is used to reduce the time it takes Web server to respond to client requests by keeping and reusing Web objects that are likely to be used in the near future in the main memory of the Web server, and by reducing the volume of data transfer between Web server and secondary storage. The heart of a caching system is its page replacement policy, which needs to make good replacement decisions when its cache is full and a new document needs to be stored. The latest and most popular replacement policies like GDSF and GDSF# use the file size, access frequency, and age in the decision process.

The effectiveness of any replacement policy can be evaluated using two metrics: hit ratio (HR) and byte hit ratio (BHR). There is always a trade-off between HR and BHR [1]. In this paper, using three different Web server logs, we use trace driven analysis to evaluate the effects of different replacement policies on the performance of a Web server. We propose a modification of GDSF# policy, IPGDSF#. Our simulation results show that our proposed replacement policy IPGDSF# performs better than several policies proposed in the literature in terms of hit rate as well as byte hit rate.