Probe and Adapt: Rate Adaptation for HTTP Video Streaming At Scale

By Zhi Li, Xiaoqing Zhu, J. Gahm, Rong Pan, Hao Hu, Ali C. Begen, D. Oran. IEEE Journal on Selected Areas in Communications, 2013

594 citations recorded by the source corpus.

Today, the technology for video streaming over the Internet is converging towards a paradigm named HTTP-based adaptive streaming (HAS), which brings two new features. First, by using HTTP/TCP, it leverages network-friendly TCP to achieve both firewall/NAT traversal and bandwidth sharing. Second, by pre-encoding and storing the video in a number of discrete rate levels, it introduces video bitrate adaptivity in a scalable way so that the video encoding is excluded from the closed-loop adaptation. A conventional wisdom in HAS design is that since the TCP throughput observed by a client would indicate the available network bandwidth, it could be used as a reliable reference for video bitrate selection. We argue that this is no longer true when HAS becomes a substantial fraction of the total network traffic. We show that when multiple HAS clients compete at a network bottleneck, the discrete nature of the video bitrates results in difficulty for a client to correctly perceive its fair-share bandwidth. Through analysis and test bed experiments, we demonstrate that this fundamental limitation leads to video bitrate oscillation and other undesirable behaviors that negatively impact the video viewing experience. We therefore argue that it is necessary to design at the application layer using a "probe and adapt" principle for video bitrate adaptation (where "probe" refers to trial increment of the data rate, instead of sending auxiliary piggybacking traffic), which is akin, but also orthogonal to the transport-layer TCP congestion control. We present PANDA - a client-side rate adaptation algorithm for HAS - as a practical embodiment of this principle. Our test bed results show that compared to conventional algorithms, PANDA is able to reduce the instability of video bitrate selection by over 75% without increasing the risk of buffer underrun.

Subfields: Computer Networks and Communications, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/9e6686e5cb0f344cb304590d87e57a46eaea7085

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Networks and Communications

In Computer Vision and Pattern Recognition

Citations in the corpus

Copa: Practical Delay-Based Congestion Control for the Internet (2018, background): “The past few years have seen new congestion control methods for datacenters [1, 2, 3, 36], cellular networks [44, 46], Web applications [12], video streaming [13, 25], vehicular Wi-Fi [11, 26], and more.”
A Survey of Machine Learning Techniques Applied to Software Defined Networking (SDN): Research Issues and Challenges (2019, background): “, BBA [175] and PANDA [176]), SDNHAS increases QoE fairness over 33%, video stability over 32% and network resource utilization over 29% on average.”
A Survey on Bitrate Adaptation Schemes for Streaming Media Over HTTP (2019, background): “Probe AND Adapt (PANDA) [53] estimates the available bandwidth accurately and tries to eliminate the ON-OFF steady state issue as well as reduce bitrate oscillations when”
A Control-Theoretic Approach for Dynamic Adaptive Video Streaming over HTTP (2015, unknown): “, [47, 34, 18, 33, 38]).”
A buffer-based approach to rate adaptation (2014, background): “Prior works have shown that sudden changes in available network capacity confuse existing ABR algorithms, causing the algorithms to either overestimate or underestimate the available network capacity [1, 2, 6, 10, 12].”
Viewport-adaptive navigable 360-degree video delivery (2016, background): “gure 3. Rate-adaptive streaming systems are based on the assumption that the selected representation will match the network conditions for the next x seconds. Rate adaptation algorithms are developed [10, 11, 12, 20, 26] to reduce the mismatch between the requested bit-rate and the throughput. In ou”
Neural Adaptive Video Streaming with Pensieve (2017, methodology): “To do this, Pensieve runs on a standalone ABR server, implemented using the Python BaseHTTPServer.”
BOLA: Near-optimal bitrate adaptation for online videos (2016, methodology): “We use the default design parameters in [9] and [10].”