QoE-Driven Adaptive K-Push for HTTP/2 Live Streaming
QoE-Driven Adaptive K-Push for HTTP/2 Live Streaming
复制标题
DOI：
10.1109/tcsvt.2018.2849015
复制
发表时间：
2019-06
影响因子：
8.4
通讯作者：
Zhimin Xu;Xinggong Zhang;Zongming Guo
中科院分区：
文献类型：
--
作者：
Zhimin Xu;Xinggong Zhang;Zongming Guo
基于HTTP的动态自适应流传输（DAS）已被广泛部署在互联网上。然而，由于HTTP/1.1的基于拉的性质，在当前DAS系统中存在不可容忍的流延迟和高请求开销。通过动态k-push，HTTP/2直播流有望以更少的开销和更小的片段持续时间实现低实时延迟。在本文中，我们提出了一个质量的经验（QoE）驱动的自适应k-push机制（QK-Push）的HTTP/2直播流。客户端只需发送一个请求，设置推送长度（$K$）和比特率（v）参数，服务器将批量推回$K$段。为了确定k-push参数，首先设计了一个概率缓冲区模型，以避免缓冲区下溢/上溢。此外，设计了三个QoE目标函数，以确保高的流传输质量（比特率），播放连续性和平滑性。QK-Push将这个多目标优化问题转化为Pareto最优问题。为了解决这个问题，纳什讨价还价解决方案的目的是平衡视频质量，比特率平滑度和请求开销的需求。最后，在每一个推动周期中的片段被选择通过求解纳什问题的离散空间拉格朗日方法。我们实现了一个HTTP/2流媒体直播原型系统，在改进的dash.js和媒体呈现描述上使用QK-Push算法。为了评估性能，进行了广泛的直播实验在可控的网络测试床和真实的互联网跟踪。实验结果表明，与现有的HTTP/1.1系统相比，QK-Push算法能够将平均比特率提高13%，将比特率振荡降低81%，将启动延迟降低58%，将平均意见评分提高12%.
Dynamic adaptive streaming (DAS) over HTTP has been widely deployed over the Internet. However, due to the pull-based nature of HTTP/1.1, there exists intolerable streaming latency and high request overhead in the current DAS systems. With dynamic k-push, HTTP/2 live streaming promises to achieve low live latency with less overhead and small segment duration. In this paper, we propose a quality of experience (QoE) driven adaptive k-push mechanism (QK-Push) for HTTP/2 live streaming. The client just sends one request to set push length ( $K$ ) and bitrate (v) parameters and the server would push back $K$ segments in a batch. To determine k-push parameters, a probabilistic buffer model is first designed to avoid buffer underflow/overflow. Also, three QoE objective functions are designed to ensure the high streaming quality (bitrate), playback continuity, and smoothness. QK-Push casts this multi-objective optimization problem as a Pareto optimal problem. To solve it, a Nash bargaining solution is designed to balance the needs for video quality, bitrate smoothness, and request overhead. Finally, the segments in each push cycle are selected by solving the Nash problem with a discrete space Lagrangian method. We implement an HTTP/2 live streaming prototype system, with the QK-Push algorithm over modified dash.js and media presentation description. To evaluate the performances, the extensive live streaming experiments are carried out over a controllable network test bed and real Internet trace. The results demonstrate that the proposed QK-Push algorithm is able to improve the average bitrate up to 13%, reduce the bitrate oscillations up to 81%, decrease the startup delay up to 58%, and increase the estimate the mean opinion score up to 12% compared to the current HTTP/1.1 system.