GroupCast: Preference-aware cooperative video streaming with scalable video coding

In this paper, we propose a Preference Aware Cooperative video streaming system for videos encoded using Scalable Video Coding (SVC) where all contributing users are interested in watching the same video on a single screen. Each user's willingness to cooperate is subjected to their own constraint such as user data plan (unlimited, 6GB, 2GB, •••, etc). Using SVC, each layer of every chunk can be fetched through only one of the cooperating users. We formulate the quality decisions of video chunks and fetching policy of the SVC layers subject to the available bandwidth, chunk deadlines, and cooperation willingness of the different users as an optimization problem. The objective is to jointly minimize the re-buffering time, maximize the average quality, and minimize the number of quality switches without violating any of the imposed constraints. We propose an offline algorithm to solve the non-convex optimization problem. This algorithm has a complexity that is polynomial in the video length and the number of cooperating users. Further, this algorithm is shown to be optimal in certain special cases. Moreover, we propose an online algorithm for more practical scenarios where erroneous bandwidth prediction for a short window is used. Simulations driven by real SVC encoded video and real bandwidth traces of a public dataset reveal the robustness and high-performance achievement of our scheme. The results motivate our next step of implementing real test bed.