Efficient streaming of live ultra high-definition videos

HTTP Adaptive Streaming (HAS) is the de facto standard for video streaming services over the Internet. In HAS, each video is temporally segmented and stored in different qualities. The client selects the quality level for every video segment based on network conditions, allowing a smoother playback and a better Quality of Experience (QoE). Although results are promising, current solutions suffer from two problems. First, a low quality and large live latency are often observed in live streaming scenarios. Second, freezes in the video playout can occur in case of sudden drops of the available bandwidth. We solved these issues using two complimentary approaches. First, we reduced the live latency using the new HTTP/2 server push feature in combination with super-short segments. Second, we designed an OpenFlow-based network controller that prioritizes the delivery of particular segments to avoid freezes at the clients. The proof-of-concept shows the results obtained when two competing clients stream a video under varying network conditions. By monitoring the clients' behavior, it is possible to clearly understand the gains brought by the proposed approaches. Particularly, we demonstrate how our solutions consistently reduce the live latency in high-RTT networks and video freezes caused by network congestion.