PROJECT TITLE :

Optimal Transcoding and Caching for Adaptive Streaming in Media Cloud: an Analytical Approach

ABSTRACT:

Nowadays, large-scale video distribution feeds a vital fraction of the global Internet traffic. However, existing content delivery networks might not be price economical enough to distribute adaptive video streaming, mainly thanks to the shortage of orchestration on storage, computing, and bandwidth resources. During this paper, we tend to leverage Media Cloud to deliver on-demand adaptive video streaming services, where those resources will be dynamically scheduled in an on-demand fashion. Our objective is to minimize the total operational cost by optimally orchestrating multiple resources. Specifically, we tend to formulate an optimization problem, by examining a 3-means tradeoff between the caching, transcoding, and bandwidth costs, at each edge server. Then, we have a tendency to adopt a two-step approach to analytically derive the closed-form resolution of the optimal transcoding configuration and caching house allocation, respectively, for each edge server. Finally, we tend to verify our resolution throughout extensive simulations. The results indicate that our approach achieves vital cost savings compared with the existing ways used in content delivery networks. In addition, we tend to additionally notice the optimal strategy and its benefits can be stricken by a list of system parameters, as well as the unit value of different resources, the hop distance to the origin server, the Zipf parameter of users’ request patterns, and therefore the settings of various bitrate versions for one segment.