Dynamic Adaptive Streaming over HTTP from Multiple Content Distribution Servers

Abstract

Dynamic adaptive streaming over HTTP (DASH\footnote{In this paper, we use DASH as a general acronym, which does not represent 3GPP- DASH/MPEG-DASH standards.}) is attractive. It reuses popular web servers rather than relying on expensive streaming server. It takes the benefits of router and firewall optimizations for HTTP traffic. It promises to automatically adapt to bandwidth dynamics to provide smooth playback experience with best achievable visual quality. In this paper, we study a new architecture for DASH, i.e. DASH from multiple content distribution servers with scalable coded video. We take the advantage of content distribution network (CDN) architecture to offer even better DASH experience. In our scheme, users request one video program simultaneously from more than one CDN servers over HTTP. To optimize resource allocation among different servers, we propose a collaborative multi-scale scheduling algorithm (CMSS) which can effectively: 1) mitigate web server load and automatically balance loads among servers; 2) adapt to bandwidth dynamics of each server; 3) optimize aggregated streaming quality. We implemented a prototype of our algorithm and deployed it on PlanetLab open platform. Measurement results verify the effectiveness of CMSS.