Strategic Prefetching of VoD Programs Based on ART2 driven Request Clustering
T. R. Gopalakrishnan Nair, P. Jayarekha · Zenodo (CERN European Organization for Nuclear Research) · 2011
In this paper we present a novel neural architecture to classify various types of VoD request arrival pattern using an unsupervised clustering Adaptive Resonance Theory 2 (ART2). The knowledge extracted from the ART2 clusters is used to prefetch the multimedia objects into the proxy server’s cache, from the disk and prepare the system to serve the clients more efficiently before the user’s arrival of the request. This approach adapts to changes in user request patterns over a period by storing the previous information. Each cluster is represented as prototype vector by generalizing the most frequently used video blocks that are accessed by all the cluster members. The simulation results of the proposed clustering and prefetching algorithm shows a significant increase in the performance of streaming server. The proposed algorithm helps the server’s agent to learn user preferences and discover the information about the corresponding videos. These videos can be prefetched to the cache and identify those videos for the users who demand it.