Design Keys to Adapt Web Prefetching Algorithms to Environment Conditions

This paper focuses on the design process of Web prefetching algorithms. The main goal of prefetching techniques in web is to reduce user perceived latency. Since these techniques present a high number of non-desired collateral effects that can negatively affect the system performance, the design process of new algorithms must be carefully performed. In a previous work we proposed some performance metrics to evaluate Web prefetching and introduced the byte recall index. In this work we present a statistical analysis which identifies how the environment conditions impact on the most significant indexes (recall and byte recall) used to evaluate prefetch algorithms. Our experimental results show that, depending on the user available bandwidth and the server processing time of each request, the recall is more correlated to the user's perceived latency than the byte recall and vice versa, so that we specify and suggest guidelines to adapt an algorithm to different environment conditions