ABSTRACT
Tracking and maintaining satisfactory QoE for video streaming services is becoming a greater challenge for mobile network operators than ever before. Downloading and watching video content on mobile devices is currently a growing trend among users, that is causing a demand for higher bandwidth and better provisioning throughout the network infrastructure. At the same time, popular demand for privacy has led many online streaming services to adopt end-to-end encryption, leaving providers with only a handful of indicators for identifying QoE issues.
In order to address these challenges, we propose a novel methodology for detecting video streaming QoE issues from encrypted traffic. We develop predictive models for detecting different levels of QoE degradation that is caused by three key influence factors, i.e. stalling, the average video quality and the quality variations. The models are then evaluated on the production network of a large scale mobile operator, where we show that despite encryption our methodology is able to accurately detect QoE problems with 72\%-92\% accuracy, while even higher performance is achieved when dealing with cleartext traffic
- Cisco. "Cisco Visual Networking Index: Global Mobile Data Traffic Forecast Update". White Paper, February 2016.Google Scholar
- Sandvine. "Global Internet Phenomena Report". December 2015.Google Scholar
- A. Finamore et al. "Is there a case for mobile phone content pre-staging?". In 9th ACM conference on Emerging networking experiments and technologies (CoNEXT), pages 321--326. ACM, 2013. Google ScholarDigital Library
- Vasona. "How encryption threatens mobile operators, and what they can do about it". http://goo.gl/fe3xpB. (Accessed on 05/11/2016).Google Scholar
- A. Rao et al. "Network Characteristics of Video Streaming Traffic". 7th ACM conference on Emerging networking experiments and technologies (CoNEXT), 2011. Google ScholarDigital Library
- R. Mok et al. "Inferring the QoE of HTTP video streaming from user-viewing activities". 1st ACM SIGCOMM workshop on Measurements up the stack (W-MUST), 2011. Google ScholarDigital Library
- Z. Guangtao et al. "Cross-Dimensional Perceptual Quality Assessment for Low Bit-Rate Videos". IEEE Transactions on Multimedia, 10(7):1316--1324, 2008. Google ScholarDigital Library
- T. Hofffeld et al. "Quanti cation of YouTube QoE via crowdsourcing". In IEEE International Symposium on Multimedia (ISM), pages 494--499. IEEE, 2011. Google ScholarDigital Library
- R. Mok et al. "Measuring the quality of experience of HTTP video streaming". In IFIP/IEEE International Symposium on Integrated Network Management (IM), pages 485--492. IEEE, 2011.Google ScholarCross Ref
- B. Lewcio et al. "Video quality in next generation mobile networks -- perception of time-varying transmission". IEEE International Workshop Technical Committee on Communications Quality and Reliability (CQR), pages 1--6, 2011.Google ScholarCross Ref
- T. Hoffeld et al. "Assessing effect sizes of in uence factors towards a QoE model for HTTP adaptive streaming". In 6th International Workshop on Quality of Multimedia Experience (QoMEX), pages 111--116. IEEE, 2014.Google Scholar
- R. Schatz et al. "Passive youtube QoE monitoring for ISPs". In Innovative Mobile and Internet Services in Ubiquitous Computing (IMIS), 2012 Sixth International Conference on, pages 358--364. IEEE, 2012. Google ScholarDigital Library
- G. Dimopoulos et al. "Analysis of YouTube user experience from passive measurements". In 9th International Conference on Network and Service Management (CNSM), pages 260--267. IEEE, 2013.Google ScholarCross Ref
- S. Krishnan et al. "Video stream quality impacts viewer behavior: inferring causality using quasi-experimental designs". Networking, IEEE/ACM Transactions on, 21(6):2001--2014, 2013. Google ScholarDigital Library
- V. Aggarwal et al. "Prometheus: toward quality-of-experience estimation for mobile apps from passive network measurements". In Proceedings of the 15th Workshop on Mobile Computing Systems and Applications, page 18. ACM, 2014. Google ScholarDigital Library
- X. Yin et al. "A Control-Theoretic Approach for Dynamic Adaptive Video Streaming over HTTP". In Proceedings of the 2015 ACM Conference on Special Interest Group on Data Communication, pages 325--338. ACM, 2015. Google ScholarDigital Library
- ES Page. "Continuous inspection schemes". Biometrika, 41(1/2):100--115, 1954.Google ScholarCross Ref
- "YouTube: Most Viewed Videos of All Time". https://www.youtube.com/playlist?list=PLirAqAtlh2r5g8xGajEwdXd3x1sZh8hC.Google Scholar
- K. Chen et al. "OneClick: A framework for measuring network quality of experience". In INFOCOM 2009, IEEE, pages 702--710. IEEE, 2009.Google ScholarCross Ref
- D. Joumblatt et al. "Predicting user dissatisfaction with internet application performance at end-hosts". In INFOCOM, pages 235--239. IEEE, 2013.Google ScholarCross Ref
- Y. Liu et al. User experience modeling for dash video. In 20th International Packet Video Workshop (PV), pages 1--8. IEEE, 2013.Google ScholarCross Ref
- A. Balachandran et al. "Developing a predictive model of quality of experience for internet video". In ACM SIGCOMM Computer Communication Review, volume 43, pages 339--350. ACM, 2013. Google ScholarDigital Library
- Z. M. Sha q et al. "Understanding the impact of network dynamics on mobile video user engagement". In ACM SIGMETRICS Performance Evaluation Review, volume 42, pages 367--379. ACM, 2014. Google ScholarDigital Library
Index Terms
- Measuring Video QoE from Encrypted Traffic
Recommendations
Machine learning assisted real-time DASH video QoE estimation technique for encrypted traffic
MHV '22: Proceedings of the 1st Mile-High Video ConferenceWith the recent rise of video traffic, it is imperative to ensure Quality of Experience (QoE). The increasing adoption of end-to-end encryption hampers any payload inspection method for QoE assessments. This poses an additional challenge for network ...
A machine learning approach to classifying YouTube QoE based on encrypted network traffic
Due to the widespread use of encryption in Over-The-Top video streaming traffic, network operators generally lack insight into application-level quality indicators (e.g., video quality levels, buffer underruns, stalling duration). They are thus faced ...
An intelligent multipath optimized link state routing protocol for QoS and QoE enhancement of video transmission in MANETs
The instability and limited resources in mobile ad hoc networks (MANETs) make the video transmission over such networks a challenging task. Transmission of video streams through multipath routing protocols in MANETs can enhance the quality of video ...
Comments