Dissecting the performance of YouTube video streaming in mobile networks

work. Summary Video streaming applications constitute a significant portion of the Internet traffic today, with mobile accounting for more than half of the online video views. The high share of video in the current Internet traffic mix has prompted many studies that examine video streaming through measurements. However, streaming performance depends on many different factors at different layers of the TCP/IP stack. For example, browser selection at the application layer or the choice of protocol in transport layer can have significant impact on the video performance. Furthermore, video performance heavily depends on the underlying network conditions (e.g., network and link layers). For mobile networks, the conditions vary significantly, since each operator has a different deployment strategy and configuration. In this paper, we focus on YouTube and carry out a comprehensive study investigating the influence of different factors on streaming performance. Leveraging the MONROE testbed that enables experimentation with 13 different network configurations in 4 countries, we collect more than 1, 800 measurement samples in operational mobile networks. With this campaign, our goal is to quantify the impact of parameters from different layers on YouTube’s streaming QoE. More specifically, we analyze the role of the browser (e.g., Firefox and Chrome), the impact of transport protocol (e.g., TCP or QUIC), the influence of network bandwidth, and signal coverage on streaming QoE. Our analysis reveals that all these parameters need to be taken into account jointly for network management practices, in order to ensure a high end-user experience.

[1]  Michael Seufert,et al.  Impact of intermediate layer on quality of experience of HTTP adaptive streaming , 2015, 2015 11th International Conference on Network and Service Management (CNSM).

[2]  Marco Ajmone Marsan,et al.  Speedtest-Like Measurements in 3G/4G Networks: The MONROE Experience , 2017, 2017 29th International Teletraffic Congress (ITC 29).

[3]  Rick McDonald,et al.  Network Fundamentals, CCNA Exploration Companion Guide , 2007 .

[4]  Andra Lutu,et al.  MONROE-Nettest: A configurable tool for dissecting speed measurements in mobile broadband networks , 2018, IEEE INFOCOM 2018 - IEEE Conference on Computer Communications Workshops (INFOCOM WKSHPS).

[5]  Phuoc Tran-Gia,et al.  Modeling the YouTube stack: From packets to quality of experience , 2016, Comput. Networks.

[6]  Zhuoqing Morley Mao,et al.  QoE Doctor: Diagnosing Mobile App QoE with Automated UI Control and Cross-layer Analysis , 2014, Internet Measurement Conference.

[7]  Marco Ajmone Marsan,et al.  Experience: An Open Platform for Experimentation with Commercial Mobile Broadband Networks , 2017, MobiCom.

[8]  Ramesh K. Sitaraman,et al.  Video Stream Quality Impacts Viewer Behavior: Inferring Causality Using Quasi-Experimental Designs , 2012, IEEE/ACM Transactions on Networking.

[9]  Özgü Alay,et al.  Concept and implementation of video QoE measurements in a mobile broadband testbed , 2017, 2017 Network Traffic Measurement and Analysis Conference (TMA).

[10]  Vaibhav Bajpai,et al.  Revealing the Load-Balancing Behavior of YouTube Traffic on Interdomain Links , 2018, PAM.

[11]  Michael Seufert,et al.  Application-layer monitoring of QoE parameters for mobile YouTube video streaming in the field , 2016, 2016 IEEE Sixth International Conference on Communications and Electronics (ICCE).

[12]  Michael Seufert,et al.  Next to You: Monitoring Quality of Experience in Cellular Networks From the End-Devices , 2016, IEEE Transactions on Network and Service Management.

[13]  Phuoc Tran-Gia,et al.  Poster: Understanding YouTube QoE in Cellular Networks with YoMoApp: A QoE Monitoring Tool for YouTube Mobile , 2015, MobiCom.

[14]  Phuoc Tran-Gia,et al.  YoMoApp: A tool for analyzing QoE of YouTube HTTP adaptive streaming in mobile networks , 2015, 2015 European Conference on Networks and Communications (EuCNC).

[15]  Michael Seufert,et al.  Exploring QoE in Cellular Networks: How Much Bandwidth do you Need for Popular Smartphone Apps? , 2015, SIGCOMM 2015.

[16]  William May,et al.  HTTP Live Streaming , 2017, RFC.

[17]  B. Staehle,et al.  YoMo: A YouTube Application Comfort Monitoring Tool , 2010 .

[18]  Phuoc Tran-Gia,et al.  Identifying QoE optimal adaptation of HTTP adaptive streaming based on subjective studies , 2015, Comput. Networks.

[19]  Yang Guo,et al.  Interactions between HTTP adaptive streaming and TCP , 2012, NOSSDAV '12.

[20]  Lea Skorin-Kapov,et al.  YouTube QoE Estimation Based on the Analysis of Encrypted Network Traffic Using Machine Learning , 2016, 2016 IEEE Globecom Workshops (GC Wkshps).

[21]  Phuoc Tran-Gia,et al.  Predicting QoE in cellular networks using machine learning and in-smartphone measurements , 2017, 2017 Ninth International Conference on Quality of Multimedia Experience (QoMEX).

[22]  Ralf Steinmetz,et al.  Subjective impression of variations in layer encoded videos , 2003, IWQoS'03.

[23]  Shobha Venkataraman,et al.  Prometheus: toward quality-of-experience estimation for mobile apps from passive network measurements , 2014, HotMobile.

[24]  Marco Mellia,et al.  YouTube everywhere: impact of device and infrastructure synergies on user experience , 2011, IMC '11.

[25]  Marco Ajmone Marsan,et al.  Measuring and assessing mobile broadband networks with MONROE , 2016, 2016 IEEE 17th International Symposium on A World of Wireless, Mobile and Multimedia Networks (WoWMoM).

[26]  Cyril Concolato,et al.  A Comparative Case Study of HTTP Adaptive Streaming Algorithms in Mobile Networks , 2017, NOSSDAV.

[27]  Phuoc Tran-Gia,et al.  Quantification of YouTube QoE via Crowdsourcing , 2011, 2011 IEEE International Symposium on Multimedia.

[28]  Ernst W. Biersack,et al.  Analyzing the impact of YouTube delivery policies on user experience , 2012, 2012 24th International Teletraffic Congress (ITC 24).

[29]  Michael Seufert,et al.  YOUQMON: a system for on-line monitoring of YouTube QoE in operational 3G networks , 2013, PERV.

[30]  Xiapu Luo,et al.  Inferring the QoE of HTTP video streaming from user-viewing activities , 2011, W-MUST '11.

[31]  Sana Ben Jemaa,et al.  A survey on YouTube streaming service , 2011, VALUETOOLS.

[32]  M. G. Michalos,et al.  Dynamic Adaptive Streaming over HTTP , 2012 .

[33]  Zhi-Li Zhang,et al.  YouTube traffic dynamics and its interplay with a tier-1 ISP: an ISP perspective , 2010, IMC '10.

[34]  Walid Dabbous,et al.  Network characteristics of video streaming traffic , 2011, CoNEXT '11.

[35]  Deep Medhi,et al.  Measurement of Quality of Experience of Video-on-Demand Services: A Survey , 2016, IEEE Communications Surveys & Tutorials.

[36]  Vincenzo Mancuso,et al.  Experimental performance evaluation of WebRTC video services over mobile networks , 2018, IEEE INFOCOM 2018 - IEEE Conference on Computer Communications Workshops (INFOCOM WKSHPS).

[37]  Andra Lutu,et al.  Results from Running an Experiment as a Service Platform for Mobile Networks , 2017, WiNTECH@MobiCom.

[38]  Henning Schulzrinne,et al.  YouSlow: a performance analysis tool for adaptive bitrate video streaming , 2014, SIGCOMM.

[39]  Shichang Xu,et al.  Dissecting VOD services for cellular: performance, root causes and best practices , 2017, Internet Measurement Conference.

[40]  Phuoc Tran-Gia,et al.  Traffic characterization of a residential wireless Internet access , 2011, Telecommun. Syst..

[41]  Lea Skorin-Kapov,et al.  A machine learning approach to classifying YouTube QoE based on encrypted network traffic , 2017, Multimedia Tools and Applications.

[42]  Andra Lutu,et al.  Open video datasets over operational mobile networks with MONROE , 2018, MMSys.

[43]  Phuoc Tran-Gia,et al.  A Survey on Quality of Experience of HTTP Adaptive Streaming , 2015, IEEE Communications Surveys & Tutorials.