Stall-Quality Tradeoff for Cloud-based Video Streaming

Video streaming over distributed storage is considered where the video segments are encoded using an erasure code for better reliability. A two-stage probabilistic scheduling is proposed to determine the subset of servers to get the data, as well as one of the parallel streams from each chosen server. The selection of video quality is also chosen with a certain probability distribution. Based on this, we formulate an optimization problem to jointly optimize the convex combination of mean stall duration and average video quality for all requests. This non-convex problem is efficiently solved using an iterative algorithm. Numerical results show significant improvement in QoE metrics for cloud-based video as compared to the considered baselines.