Adaptive Streaming: The Network HAS to Help

摘要

HTTP adaptive streaming (HAS) is becoming popular for video delivery because it dynamically provides high quality content. A HAS client does this by requesting a small chunk of video at a time, selecting the chunk quality based on inferred network conditions and its own buffer state. Because chunks are requested using Hypertext Transfer Protocol (HTTP), they traverse firewalls and are cacheable like any other Web content. Even though HAS is compatible with existing infrastructure, HAS's near-real time demands and the new request patterns it causes require an understanding of the interaction between the network and HAS algorithms. In this paper, we evaluate the responsiveness of HAS algorithms under dynamic conditions and how it affects the overall user experience as well as key infrastructure resources, particularly intermediate caches. Relevant scenarios we evaluate include varying delays, available bandwidth, cache response times, and interaction with competing traffic.