ViCrypt to the Rescue: Real-Time, Machine-Learning-Driven Video-QoE Monitoring for Encrypted Streaming Traffic
| Autor: | Michael Seufert, Sarah Wassermann, Kuang Li, Li Gang, Pedro Casas |
|---|---|
| Přispěvatelé: | Austrian Institute of Technology [Vienna] (AIT), University of Würzburg, Huawei Technologies [Shenzhen] |
| Rok vydání: | 2020 |
| Předmět: |
Computer Networks and Communications
Network packet business.industry Computer science Real-time computing Feature extraction [INFO.INFO-MM]Computer Science [cs]/Multimedia [cs.MM] 020206 networking & telecommunications 02 engineering and technology Encryption Display resolution Session (web analytics) Machine Learning [INFO.INFO-NI]Computer Science [cs]/Networking and Internet Architecture [cs.NI] [INFO.INFO-LG]Computer Science [cs]/Machine Learning [cs.LG] 0202 electrical engineering electronic engineering information engineering Key (cryptography) Encrypted Traffic The Internet Network Monitoring QoE State (computer science) Electrical and Electronic Engineering business |
| Zdroj: | IEEE Transactions on Network and Service Management IEEE Transactions on Network and Service Management, IEEE, 2020, 17 (4), pp.2007-2023. ⟨10.1109/TNSM.2020.3036497⟩ |
| ISSN: | 2373-7379 1932-4537 |
| DOI: | 10.1109/tnsm.2020.3036497 |
| Popis: | International audience; Video streaming is the killer application of the Internet today. In this paper, we address the problem of realtime, passive Quality-of-Experience (QoE) monitoring of HTTP Adaptive Video Streaming (HAS), from the Internet-Service-Provider (ISP) perspective-i.e., relying exclusively on innetwork traffic measurements. Given the wide adoption of endto-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 MLdriven 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 largescale 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 coarsegrained 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 videostreaming services such as Netflix and Amazon. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|