arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2403.16985cs.MM
收藏

迈向低延迟与高能效的混合P2P-CDN直播视频流

Towards Low-Latency and Energy-Efficient Hybrid P2P-CDN Live Video Streaming

Reza Farahani, Christian Timmerer, Hermann Hellwagner

AI总结:

本文提出一种基于NFV和边缘计算的混合P2P-CDN直播视频流框架,通过多层架构和动作树高效分配视频获取与转码任务,实验证明其有效提升用户QoE、降低延迟并减少边缘服务器能耗。

摘要:

通过超文本传输协议(HTTP)传输分段视频在直播和视频点播(VoD)应用中日益普及。然而,设计一个可扩展且适应性强的框架,以降低服务器能耗并支持低延迟和高质量服务(特别是在直播视频流场景中),对于OTT(Over-The-Top)服务提供商而言仍具挑战。为应对这些挑战,本文提出了一种新型混合P2P-CDN框架,利用网络功能虚拟化(NFV)和边缘计算等新型网络与计算范式进行直播视频流。该框架引入了多层架构及相应的可能动作树,综合考虑来自对等节点、边缘和CDN服务器的所有可用资源,以在混合P2P-CDN网络中高效分配视频获取和转码任务,从而改善用户延迟和视频质量。我们还讨论了为验证该框架而设计的测试平台,并将其与基线方法进行了比较。实验结果表明,与基线方法相比,该框架提升了用户体验质量(QoE),降低了客户端服务延迟,并改善了边缘服务器的能耗。

英文摘要:

Streaming segmented videos over the Hypertext Transfer Protocol (HTTP) is an increasingly popular approach in both live and video-on-demand (VoD) applications. However, designing a scalable and adaptable framework that reduces servers energy consumption and supports low latency and high quality services, particularly for live video streaming scenarios, is still challenging for Over-The-Top (OTT) service providers. To address such challenges, this paper introduces a new hybrid P2P-CDN framework that leverages new networking and computing paradigms, i.e., Network Function Virtualization (NFV) and edge computing for live video streaming. The proposed framework introduces a multi-layer architecture and a tree of possible actions therein (an action tree), taking into account all available resources from peers, edge, and CDN servers to efficiently distribute video fetching and transcoding tasks across a hybrid P2P-CDN network, consequently enhancing the users latency and video quality. We also discuss our testbed designed to validate the framework and compare it with baseline methods. The experimental results indicate that the proposed framework improves user Quality of Experience (QoE), reduces client serving latency, and improves edge server energy consumption compared to baseline approaches.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑