Streaming video over HTTP with consistent quality

Abstract

In conventional HTTP-based adaptive streaming (HAS), a video source is encoded at multiple levels of constant bitrate representations, and a client makes its representation selections according to the measured network bandwidth. While greatly simplifying adaptation to the varying network conditions, this strategy is not the best for optimizing the video quality experienced by end users. Quality fluctuation can be reduced if the natural variability of video content is taken into consideration. In this work, we study the design of a client rate adaptation algorithm to yield consistent video quality. We assume that clients have visibility into incoming video within a finite horizon. We also take advantage of the client-side video buffer, by using it as a breathing room for not only network bandwidth variability, but also video bitrate variability. The challenge, however, lies in how to balance these two variabilities to yield consistent video quality without risking a buffer underrun. We propose an optimization solution that uses an online algorithm to adapt the video bitrate step-by-step, while applying dynamic programming at each step. We incorporate our solution into PANDA -a practical rate adaptation algorithm designed for HAS deployment at scale.

Optimal Selection of Adaptive Streaming Representations

“…The general objective is to maximize the Quality of Experience (QoE) for the users while avoiding unnecessary quality fluctuations. For example, the selection of the representation can be optimized in such a way that large variations of rates in successive segments are avoided, since large rate variations may lead to an unpleasant viewing experience [15], [16], [17]. Other solutions for the controller have also been investigated in order to minimize the re-buffering phases [12], [15].…”

“…For example, the selection of the representation can be optimized in such a way that large variations of rates in successive segments are avoided, since large rate variations may lead to an unpleasant viewing experience [15], [16], [17]. Other solutions for the controller have also been investigated in order to minimize the re-buffering phases [12], [15]. On a more general perspective, it has been shown that the current HTTP-adaptive streaming systems have limitations when a large number of clients share the same network [18].…”

A Scalable User Fairness Model for Adaptive Video Streaming Over SDN-Assisted Future Networks

“…Using video-quality fairness, switching-impact fairness, and cost-efficiency fairness as the user-level historical session status, it is possible to employ techniques such as dynamic programming to improve runtime performance [21]. Stateful metrics like SI require historical information related to quality switches of the video session, hence it is more difficult to reduce their runtime complexity.…”

Online learning adaptation strategy for DASH clients

“…In [4], the authors propose a receding horizon optimization for the representation selection aimed at maximizing their quality while reducing quality variations. The proposed adaptation logic leads to good and stable quality values during the video streaming session.…”

“…Moreover, while the playback buffer can absorb some of the bitrate variations, rebuffering events are still frequent in highly dynamic network environments. The only viable solution to preserve a good buffer level while maximizing QoE is to implement foresighted optimization in the adaptation logic [4]; however, most of the existing optimization techniques require a priori information about the dynamics of the system, which are usually not available in practice. An efficient online adaptation logic should therefore be able to learn the best representation selection strategy that maximizes the long term reward.…”