Performance of Low-Latency DASH/CMAF and Low-Latency HLS Streaming Systems

Yuriy Reznik, Thiago Teixeira, Bo Zhang

Reducing end-to-end streaming latency is critical to HTTP-based live video streaming. There are currently two technologies in this domain: Low-Latency HLS (LL-HLS) and Low-Latency DASH (LL-DASH). The latter is sometimes also referred to as Low-Latency CMAF (LL-CM.AF), but effectively it is the same architecture. Several existing implementations of streaming players, as well as encoding and packaging tools, support both technologies. Well-known examples include Apple's AVplayer, Shaka player, HLS.js, DASH.js, FFmpeg, etc. In this paper, we conduct a performance analysis of such streaming systems. We perform a series of live streaming experiments, repeated using identical video content, encoders, encoding profiles, and network conditions, emulated by using traces of real-world networks. We capture several performance metrics, such as average stream bitrate, the amounts of downloaded media data, streaming latency, buffering, frequency of stream switching, etc. Subsequently, we analyze the captured data and describe the observed differences in the performance of LL-HLS and LL-DASH-based systems.

Published
2021-11
Content type
Original Research
DOI
10.5594/M001943