Skip to Main Content
The popularity of Web objects, and by extension the popularity of the Web sites, besides the appearance of clear footprints in user's accesses that show a considerable spatial locality, make possible to predict future accesses based on the current ones. This fact permits to implement also prefetching techniques in Web architecture in order to reduce the latency perceived by the users. Although the open literature presents some approaches in this sense, the huge variety of prefetching algorithms, and the different scenarios and conditions where they are applied make very difficult to compare performance and to obtain correct conclusions that permit researchers to improve their proposals or even detect in which conditions one solution is more convenient than others. This is the main reason why we propose A new and free available environment in order to implement and study prefetching techniques efficiently. Our framework is a hybrid implementation that combines both real and simulated parts in order to provide flexibility and accuracy. It reproduces in detail the behavior of Web users, proxy severs and original servers. The simulator also includes a module to provide performance results, such as precision (prefetching accuracy), recall, response time, and byte transference.