Web cache optimization with nonlinear model using object features

Abstract

In this paper, Web cache optimization by utilizing syntactic features extracted from cache objects is studied. A nonlinear model is used to predict the value of each cache object by using features from the HTTP responses of the server, the access log of the cache, and from the HTML structure of the object. In a case study, linear and nonlinear models are used to classify about 50,000 HTML documents according to their popularity. The nonlinear model yields classification percentages of 64 and 74 for the documents to be stored or to be removed from the cache, respectively. A synthetic workload is then used to study the performance gain from the classifier in a conventional Least Recently Used cache model. The results suggest that the proposed approach can improve the performance of the cache substantially.