Analysis of an efficient pre-fetching algorithm for scalable contents over content delivery networks

Recently it has been shown that scalable (layered) image is appropriate for the Internet because of its better flexibility and functionality. At the same time, the prefetching technology also proves to be an efficient method to improve the performance of image-delivery with the low delay and adjustable quality. However, how to deploy the pre-fetching to deliver scalable contents has not been mentioned. Therefore, this paper presents an analysis of the pre-fetching algorithm to deliver layered image contents over the Internet. Based on the analysis of web request probability and the relations between different layers in the scalable imaging delivering system, a new pre-fetching algorithm is proposed to drastically improve cache performance. This proposal is a request frequencybased approach, in which a progressive image format can be used.