Abstract
The increasing demand for World Wide Web (WWW) services has led to a considerable increase in the amount of Internet traffic. As a result, the network becomes highly prone to congestion which increases the load on servers, resulting in increasing the access times of WWW documents. Thus, web caching is crucial for reducing the load on network, shorten network latency and improve clients' waiting time. Many web cashing systems and policies have been proposed to determine which objects to evict from the cache memory to accommodate new ones. Most of these systems and policies are mainly based on the enhancement of a well-known scheme called the Least Frequently Used (LFU) scheme. Although most of the proposed schemes could overcome the disadvantages of the LFU, they still have lots of overhead and are difficult to implement. This work proposes replacement approaches with better characteristics as they are easier to be implemented than the previous approaches. The proposed approaches consider the internal requests generated in each web site. We added this factors to two famous approaches; LFU and Weighting Replacement Policy (WRP) to strength their performance. The experimental results indicate the superiority of the proposed approaches compared to both LFU and WRP, in terms of improvement in cache performance.