An efficient web page allocation on a server using adaptive neural networks

Abstract

In this paper, we present a novel application of connectionist neural modeling to map web page requests to web server cache to maximize hit ratio and at the same time balance the conflicting request of distributing the web requests equally among web caches. In particular, we describe and present a new learning algorithm for a fast Web page allocation on a server using self-organizing properties of neural network. We present a prefetching scheme in which we apply our clustering technique to group users and then prefetch their requests according to the prototype vector of each group. Our prefetching scheme has prediction accuracy as high as 98.18%. A detailed experimental analysis is presented in this paper. © Springer-Verlag Berlin Heidelberg 2005.