Delay-constrained rate control for real-time video streaming over wireless networks

Rate control is a big challenge for real-time video streaming on the internet with the needs of low latency, bandwidth-consuming and stable video rate. However, most of the existing Internet congestion control protocols ignore these needs, and some of them use the packet loss event as congestion signal which is deviation especially over error-prone wireless networks. In this paper, we propose a delay-constrained rate control algorithm by locking queueing delay onto a desired objective. The shadow price of video rate is controlled by queueing delay. All flows adapt video rate according to distortion weight and shadow price so as to achieve a distributed bandwidth sharing with low latency, efficient utilization, and distortion fairness. A closed-loop rate control system is designed for the purpose of stable and agile control. The control parameters are analyzed using control-theoretic approach. Additionally, we construct a real-time wireless video streaming test-bed and conduct extensive experiments over it. Compared with the current widely used methods, the experimental results show that the proposed algorithm can achieve 3dB or more gains in PSNR, and better performance on bandwidth utilization, flow stability with well guaranteed multi-flow fairness.