RnB: rate and brightness adaptation for rate-distortion-energy tradeoff in HTTP adaptive streaming over mobile devices
作者: Zhisheng Yan, Chang Wen Chen
摘要
Video streaming is a prevalent mobile service that drains a significant amount of battery power. While various efforts have been made toward saving both video transfer and display energy, they are independently designed in an ad-hoc way and thereby can cause some non-apparent yet critical performance issues. To fill in this gap, this paper presents a fundamentally new design by jointly considering the end-to-end pipeline from the initial video encoding to the final mobile display. In essence, we shift the classic R-D tradeoff that has governed streaming system designs for decades to a fresh rate-distortion-energy (R-D-E) tradeoff specifically tailored for mobile devices. We present RnB, a video bitrate and display brightness adaptation platform that is standard-compliant, backward compatible, and device-neutral in order to achieve the proposed R-D-E tradeoff. RnB is empowered by some new discovery about the inherent relationship among bitrate, display brightness, and video quality as well as by an control-theoretic formulation to dynamically adapt the bitrate and scale the display brightness. Experimental results based on real-time implementation show that RnB can achieve an average of 19% energy reduction with final video quality comparable to conventional R-D based schemes.