当前位置: X-MOL 学术IEEE Trans. Netw. Serv. Manag. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
ViCrypt to the Rescue: Real-time, Machine-Learning-driven Video-QoE Monitoring for Encrypted Streaming Traffic
IEEE Transactions on Network and Service Management ( IF 4.7 ) Pub Date : 2020-12-01 , DOI: 10.1109/tnsm.2020.3036497
Sarah Wassermann , Michael Seufert , Pedro Casas , Li Gang , Kuang Li

Video streaming is the killer application of the Internet today. In this article, we address the problem of real-time, passive Quality-of-Experience (QoE) monitoring of HTTP Adaptive Video Streaming (HAS), from the Internet-Service-Provider (ISP) perspective – i.e., relying exclusively on in-network traffic measurements. Given the wide adoption of end-to-end encryption, we resort to machine-learning (ML) models to estimate multiple key video-QoE indicators (KQIs) from the analysis of the encrypted traffic. We present ViCrypt, an ML-driven monitoring solution able to infer the most important KQIs for HTTP Adaptive Streaming (HAS), namely stalling, initial delay, video resolution, and average video bitrate. ViCrypt performs estimations in real-time, during the playback of an ongoing video-streaming session, with a fine-grained temporal resolution of just one second. For this, it relies on lightweight, stream-like features continuously extracted from the encrypted stream of packets. Empirical evaluations on a large and heterogeneous corpus of YouTube measurements show that ViCrypt can infer the targeted KQIs with high accuracy, enabling large-scale passive video-QoE monitoring and proactive QoE-aware traffic management. Different from the state of the art, and besides real-time operation, ViCrypt is not bound to coarse-grained KQI-classes, providing better and sharper insights than other solutions. Finally, ViCrypt does not require chunk-detection approaches for feature extraction, significantly reducing the complexity of the monitoring approach, and potentially improving on generalization to different HAS protocols used by other video-streaming services such as Netflix and Amazon.

中文翻译:

ViCrypt 拯救世界:实时、机器学习驱动的视频 QoE 监控加密流媒体流量

视频流是当今互联网的杀手级应用。在本文中,我们从互联网服务提供商 (ISP) 的角度解决了 HTTP 自适应视频流 (HAS) 的实时、被动体验质量 (QoE) 监控问题——即,完全依赖于- 网络流量测量。鉴于端到端加密的广泛采用,我们采用机器学习 (ML) 模型,通过对加密流量的分析来估计多个关键视频 QoE 指标 (KQI)。我们提出了 ViCrypt,这是一种 ML 驱动的监控解决方案,能够推断 HTTP 自适应流 (HAS) 最重要的 KQI,即停顿、初始延迟、视频分辨率和平均视频比特率。ViCrypt 在播放正在进行的视频流会话期间实时执行估计,具有仅一秒的细粒度时间分辨率。为此,它依赖于从加密的数据包流中连续提取的轻量级、类似流的特征。对 YouTube 测量的大型异构语料库的实证评估表明,ViCrypt 可以高精度地推断出目标 KQI,从而实现大规模被动视频 QoE 监控和主动 QoE 感知流量管理。与现有技术不同,除了实时操作外,ViCrypt 不受粗粒度 KQI 类的约束,提供比其他解决方案更好、更敏锐的洞察力。最后,ViCrypt 不需要块检测方法来提取特征,显着降低了监控方法的复杂性,
更新日期:2020-12-01
down
wechat
bug