Neural Network Based Prefetching Control Mechanism

Abstract

An important issue incurred by users that limits the use of internet is the long web access delays. Most efficient way to solve this problem is to use “Prefetching”. This paper is an attempt to dynamically monitor the network bandwidth for which a neural network-based model has been worked upon. Prefetching is an effective and efficient technique for reducing users perceived latency. It is a technique that predicts & fetches the web pages in advance corresponding to the clients’ request, that will be accessed in future. Generally, this prediction is based on the historical information that the sever maintains for each web page it serves in a chronological order. This is a speculative technique where if predictions are incorrect then prefetching adds extra traffic to the network, which is seriously negating the network performance. Therefore, there is critical need of a mechanism that could analyze the network bandwidth of the system before prefetching is done. Based on network conditions, this model not only guides if the prefetching should be done or not but also tells number of pages which are to be prefetched in advance so that network bandwidth can be effectively utilized. Proposed control mechanism has been validated using NS-2 simulator and thus various adverse effects of prefetching in terms of response time and bandwidth utilization have been reduced.