Cache replacement strategies for scalable video streaming in CCN

Abstract

To deal with the structural limitations of the current Internet, a new concept of a future Internet has been suggested, among which a content centric network(CCN) with in-router storage and the use of content as an address has taken center stage. We describe the design and implementation of new cache-replacement algorithms for layered video content(H.264/SVC) streaming in a CCN. The cache-replacement algorithms(LGD-size, and Lmix)proposed in this paper impose value on each object based on its size, recent reference trend, and the reference frequency stored in the cache. In addition, the proposed algorithms operate by reflecting the layered features of SVC video streaming. The proposed algorithms are applied to a CCN node, and when a client repeatedly requests HTTP adaptive video-streaming encoded with H.264/SVC, the existing algorithms(FIFO, LFU, LRU) and cache hit rates of each CCN node are measured. A comparison of the cache hit rate at each CCN node and the quality of the video streaming, show that the efficiency of layered video streaming in a CCN can be improved by modifying the cache-replacement algorithm used.