A Control-Theoretic Approach for Dynamic Adaptive Video Streaming over HTTP

Abstract

User-perceived quality-of-experience (QoE) is critical in Internet video applications as it impacts revenues for content providers and delivery systems. Given that there is little support in the network for optimizing such measures, bottlenecks could occur anywhere in the delivery system. Consequently, a robust bitrate adaptation algorithm in client-side players is critical to ensure good user experience. Previous studies have shown key limitations of state-of-art commercial solutions and proposed a range of heuristic fixes. Despite the emergence of several proposals, there is still a distinct lack of consensus on: (1) How best to design this client-side bitrate adaptation logic (e.g., use rate estimates vs. buffer occupancy); (2) How well specific classes of approaches will perform under diverse operating regimes (e.g., high throughput variability); or (3) How do they actually balance different QoE objectives (e.g., startup delay vs. rebuffering). To this end, this paper makes three key technical contributions. First, to bring some rigor to this space, we develop a principled control-theoretic model to reason about a broad spectrum of strategies. Second, we propose a novel model predictive control algorithm that can optimally combine throughput and buffer occupancy information to outperform traditional approaches. Third, we present a practical implementation in a reference video player to validate our approach using realistic trace-driven emulations.

Optimized Adaptive Streaming of Multi-video Stream Bundles

“…However, linear models weighting playback quality and stalls have been used in other contexts. For example, Yin et al [12] use the linear combination of the average video quality, the average quality variation, the rebuffering times, and the startup delay to capture the quality of experience for linear video. Here, we instead focus on the presence (or absence) of stalls, rather than their duration, and do not model quality variations.…”

Traffic prediction methods for quality improvement of adaptive video

“…For the prediction, the authors employed an autoregressive model, a support vector regression and ANNs. In [20], the authors study the effect of prediction errors on the performance of three adaptation approaches, buffer based, rate based, and model predictive control. As a predictor, the authors use a harmonic mean of past throughput measurements.…”

ARBITER: Adaptive rate-based intelligent HTTP streaming algorithm

“…The authors propose three heuristics that use online or offline estimates for bandwidth statistics to accommodate MDP complexity. In [5], Yin et al propose model predictive control (MPC) as a QoE optimised adaptation framework that combines both network and application status. Additionally, they propose a heuristic by quantising their decision parameter space.…”

“…Many of the algorithms [6,7,4,5] employ a harmonic mean estimator, which tends to be conservative and could lead to streaming low video quality and under-utilising the system resources. ARBITER adopts a different approach by employing adaptively scaling its estimate based on the second moment of the throughput samples.…”

“…The state-of-the-art in adaptive streaming algorithms can be generally classified as buffer-based [3], rate-based [4], and hybrid strategies [5,6]. In wireless systems, the channel fea-978-1-4799-0000-0 tures temporal variations due to its multi-path nature, user mobility, and medium sharing.…”