A Simple Yet Robust Caching Algorithm Based on Dynamic Access Patterns.pdfVIP

A Simple Yet Robust Caching Algorithm Based on Dynamic Access Patterns James E. Pitkow Margaret M. Recker Graphics, Visualization, Usability Center College of Computing Georgia Institute of Technology Atlanta, GA 30332-0280 U.S.A. Email {pitkow, mimi}@ ABSTRACT The World-Wide Web continues its remarkable and seemingly unregulated growth. This growth has seen a corresponding increase in network loads and user response times. One common approach for improving the retrieval rate of large, distributed documents is via caching. In this paper, we present a caching algo- rithm that flexibly adapt its parameters to the hit rates and access patterns of users requesting documents. The algorithm is derived from an analysis of user accesses in a WWW database. In particular, the analysis is based upon a model from psychological research on human memory, which has long studied retrieval of memory items based on frequency and recency rates of past item occurrences. Results show that the model predicts document access with a high degree of accuracy. Furthermore, the model indicates that a caching algorithm based upon the recency rates of prior document access will reliably handle future docu- ment requests. The algorithm presented is simple, robust, and easily implementable. INTRODUCTION By all indications, the World-Wide Web, or WWW (Berners-Lee, et. al. 1992; Berners-Lee, et. al. 1994), continues its remarkable and seemingly unregulated growth. The rapid growth in the number of users and hosts, information servers (Beebee 1994; Gray, 1994), and network