A Comparative Case Study of HTTP Adaptive Streaming Algorithms in Mobile Networks

Abstract

HTTP Adaptive Streaming (HAS) techniques are now the dominant solution for video delivery in mobile networks. Over the past few years, several HAS algorithms have been introduced in order to improve user quality-of-experience (QoE) by bit-rate adaptation. eir di erence is mainly the required input information, ranging from network characteristics to application-layer parameters such as the playback bu er. Interestingly, despite the recent outburst in scienti c papers on the topic, a comprehensive comparative study of the main algorithm classes is still missing. In this paper we provide such comparison by evaluating the performance of the state-of-the-art HAS algorithms per class, based on data from eld measurements. We provide a systematic study of the main QoE factors and the impact of the target bu er level. We conclude that this target bu er level is a critical classi er for the studied HAS algorithms. While bu er-based algorithms show superior QoE in most of the cases, their performance may di er at the low target bu er levels of live streaming services. Overall, we believe that our ndings provide valuable insight for the design and choice of HAS algorithms according to networks conditions and service requirements.

Improving Video Delivery with Fourier Analysis of Traffic in Multi-Access Edge Computing

“…In our initial measurements, using a setup discussed in Sec. 3.2, we observe a specific periodical pattern, which is typical for video delivery with DASH AVC using buffer-based adaptation algorithms confirmed by other sources [5,6,14]. The traffic requested by the client appears as a periodical rectangle function (i.e., a channel is periodically occupied and idle with a certain frequency).…”

“…Buffer-based video streaming considers the buffer fill level to keep/improve the quality of the subsequent segment, if the necessary buffer refill level was experienced while downloading previous segments. Karagkioules et al [6] surveys different adaptation algorithms. It is worth noting that there exist different kinds of video encodings and this work focuses on video delivery with DASH Advanced Video Coding (AVC).…”

“…Using a notebook connected to a smart phone Moto 2 6 , we run the video stream for approximately 90 seconds, while moving the phone according to the mobility pattern (c.f., Fig. 7).…”

DASHing towards hollywood

“…As a first step towards developing better adaptation algorithms for such use cases, we modified the widely used adaptation algorithm, Buffer Occupancy based Lyapunov Algorithm (BOLA). BOLA is a buffer-based algorithm that performs well in a variety of network conditions [87,44]. Algorithm 1 shows the download operation with BOLA in a TCP DASH client.…”

“…Others use the time to download a chunk as the main metric for estimation [11]. However, there is general consensus among researchers that buffer based algorithms that utilise the length of playout buffer (the duration of the video that has already been prebuffered at the client) as the primary indicator for quality estimation perform better [87,44,39]. Most clients would use a mix of indicators for the estimation and additional rules 1 www.matroska.org, www.webmproject.org…”