Metafile-Based Scalable Caching and Dynamic Replacing Algorithms for Multiple Videos Over Quality-of-Service Networks

This paper presents metafile-based scalable caching and dynamic replacing algorithms for multiple videos over quality-of-service networks. A metafile for each video includes the cached-frame sequence, which is made by scalable caching algorithm minimizing client's buffer size and channel bandwidth under the general video traffic condition. Based on the metafiles, we propose a caching algorithm for multiple videos to effectively reduce both the buffer size and the required bandwidth and replacing algorithm to dynamically update the cached frames when user access pattern changes. Finally, experimental results are provided to compare the proposed algorithms with various existing caching and replacing algorithms.