Energy Efficient Proxy Prefetch-Cache Framework in Clustered Architecture

The dynamic nature and explosive growth of the World Wide Web (WWW) makes a big challenge for retrieving and satisfying the Web clients of multiple varieties of interests with updated information and documents around the globe. Due to enormous traffic in the network and various constraints such as limited bandwidth availability, processing time at server, round trip delay etc., the Web latency is increasing continuously. A proxy based hybrid cache-prefetch model with Web log mining technique is the most attractive and successful solution to reduce this latency and to improve Web Quality of Service. Also, in today’s eco-friendly computing world low power consumption and efficient energy management of individual hardware components, system software, to network applications is a critical and urgent issue. To address these issues, we propose an Energy Efficient Intelligent Agent (IA) controlled combined proxy prefetch-cache framework in clustered architecture. The proposed framework will satisfy most of the clients’ requests through a local proxy cache populated from various distributed proxies within same or neighbouring clusters and very few requests are sent to the remote origin servers. It also keeps network congestion minimum by providing high hit ratio (HR) and byte hit ratio (BHR) through prefetching and minimize Web latency. We have also developed a Power-Performance model along with some guidelines for energy efficient design solutions to be adopted into our proposed framework. The performance of the proposed architecture is evaluated using hit ratio and latency time of requests depending on varying cache size and user load. The results obtained show that the proposed scheme is effective in comparison to the existing techniques used individually with respect to the above Web metrics. Keywords— Prefetch-Cache framework,Distributed clustered architecture, Hybrid Proxy caching, Hit ratio, Response time.