Multicast with cache (Mcache): An adaptive zero-delay video-on-demand service

A closed-loop (demand-driven) approach toward video-on-demand services, cal led multicast cache (Mcache), is discussed in this paper. Servers use multi cast to reduce their bandwidth usage by allowing multiple requests to be se rved with a single data stream. However, this requires clients to delay rec eiving the movie until the multicast starts. Using regional cache servers d eployed over many strategic locations, Mcache can remove the initial playou t delays of clients in multicast-based video streaming. While requests are hatched together for a multicast, clients can receive the prefix of a reque sted movie clip from caches located in their own regions. The multicast con taining the later portion of the movie can wait until the prefix is played out. While this use of regional caches has been proposed previously, the no velty of our scheme lies in that the requests coming after the multicast st arts can still be batched together to be served by multicast patches withou t any playout delays. The use of patches was proposed before, but they are used either with unicast or with playout delays. Mcache effectively hires t he idea of a multicast patch with caches to provide a truly adaptive video- on-demand service whose bandwidth usage is up to par with the best known op en-loop schemes under high request rates while using only minimal bandwidth under low request rates. In addition, efficient use of multicast and cache s removes the need for a priori knowledge of client disk storage requiremen ts which some of the existing schemes assume. This makes Mcache ideal for t he current heterogeneous Internet environments where those parameters are h ard to predict. We further propose the Segmented Mcache (SMcache) scheme wh ich is a generalized and improved version of Mcache where the clip is parti tioned into several segments in order to preserve the advantages of the ori ginal Mcache scheme with nearly the same server bandwidth requirement as th e open loop schemes under high request rates.