Efficient Upstream Bandwidth Multiplexing for Cloud Video Recording Services
Efficient Upstream Bandwidth Multiplexing for Cloud Video Recording Services
复制标题
DOI：
10.1109/tcsvt.2015.2475875
复制
发表时间：
2016-10
影响因子：
8.4
通讯作者：
Jian-Qian He;Di Wu;Xueyan Xie;Min Chen;Yong Li;Guoqing Zhang
中科院分区：
文献类型：
--
作者：
Jian-Qian He;Di Wu;Xueyan Xie;Min Chen;Yong Li;Guoqing Zhang
云视频（CVR）的热潮越来越受到公众和企业家的关注。通过将实时视频记录存档在云中，CVR范例可以随时随地跟踪监控区域的活动，从而实现各种智能服务。然而，当多个分布式摄像机共用同一上行链路时，有限的上行带宽会影响监控质量。为了解决这一问题，本文提出了一种高效的上游带宽复用算法，从CVR用户的角度出发，为每个直播视频流智能分配上游带宽，同时最大化整体效用。具体来说，我们将上游带宽复用问题表述为一个约束随机优化问题，并应用层次逼近技术有效地求解了该问题。我们的算法可以扩展到考虑视频流的优先级，为优先级高的视频流分配更多的上游带宽。我们明确地证明了该算法的近似比。此外，我们还进行了大量的跟踪驱动模拟来验证我们算法的有效性。仿真结果表明，与其他算法相比，我们的算法将CVR用户的整体效用提高了20%以上，并且即使视频流数量增加，每个带宽单位的平均效用也能保证稳定。
The upsurge of cloud video recording (CVR) has gained increasing attention from the general public and entrepreneurs. With live video records archived in the cloud, the CVR paradigm enables various smart services by keeping track of activities in the monitored region from anywhere at any time. However, the limited upstream bandwidth affects the quality of surveillance when multiple distributed cameras share the same upstream link. To solve the problem, this paper proposes an efficient upstream bandwidth multiplexing algorithm to intelligently allocate upstream bandwidth for each live video stream while maximizing the overall utility from the perspective of a CVR user. Specifically, we formulate the upstream bandwidth multiplexing problem as a constrained stochastic optimization problem, and apply the technique of hierarchical approximation to solve it efficiently. Our algorithm can be extended to take the priority of video streams into account and allocate more upstream bandwidth to video streams with higher priorities. We explicitly prove the approximation ratio of the proposed algorithm. In addition, we also conduct extensive trace-driven simulations to verify the effectiveness of our algorithm. The simulation results show that our algorithm improves the overall CVR user utility by over 20% compared with other alternatives, and the average utility per bandwidth unit is guaranteed to be stable even when the number of video streams increases.