Towards Agile and Smooth Video Adaptation in HTTP Adaptive Streaming

HTTP Adaptive Streaming (HAS) is widely deployed on the Internet for live and on-demand video streaming services. Video adaptation algorithms in the existing HAS systems are either too sluggish to respond to congestion level shifts or too sensitive to short-term network bandwidth variations. Both degrade user video experience. In this paper, we formally study the tradeoff between responsiveness and smoothness in HAS through analysis and experiments. We show that client-side buffered video time is a good feedback signal to guide video adaptation. We then propose novel video rate control algorithms that balance the needs for video rate smoothness and high bandwidth utilization. We show that a small video rate margin can lead to much improved smoothness in video rate and buffer size. We also propose HAS designs that can work with multiple servers and wireless connections. We develop a fully functional HAS system and evaluate its performance through extensive experiments on a network testbed and the Internet. We demonstrate that our HAS designs are highly efficient and robust in realistic network environment.