Intelligent cooperative web caching policies for media objects based on decision tree supervised machine learning algorithm

Delivering media objects to the end users is one of the advantages of World Wide Web (WWW). Web caching plays a key role in this advantage. However, the size of the cache is limited which is considered as one of the drawbacks of web caching. Furthermore, retrieving the same media object from the origin server many times consumes the network bandwidth. Moreover, cache pollution is a drawback of traditional web caching policies such as Least Frequently Used (LFU), Least Recently Used (LRU), and Greedy Dual Size (GDS) where web objects that are stored in the cache are not visited frequently. In this work, new intelligent cooperative web caching approaches based on decision tree supervised machine learning algorithm are presented. A simulation is carried out to evaluate the performance of the proposed approaches. The results show that the new approaches improve the performance of the traditional web caching policies