Video Delivery Performance of a Large-Scale VoD System and the Implications on Content Delivery

Video delivery performance is the main factor that affects Internet video quality. Characterizing the video delivery performance, especially the delivery throughput, can help content providers as well as Internet service providers (ISPs) in system optimization and network planning. Based on a unique dataset consisting of 20 million video download speed measurements , this paper comprehensively studies the video delivery throughput of a large-scale commercial video-on- demand (VoD) system. We observe that user speed exhibits a large variation over time of day as well as across provincial locations. In particular, the worst performance of day is 30% lower than the peak performance . The analysis also reveals that video download speed has a notable impact on Internet video quality, which in turn influences user engagement . The impact, however, becomes limited when the speed increases beyond a certain threshold, which is mostly dependent on the video encoded bitrates. We further examine the interaction between Internet infrastructure and video delivery throughput using the linear regression model and find that crossing the ISP or regional network border yields 15-20% speed loss. Based on these observations , we finally evaluate the potential of edge caching and hybrid CDN-P2P in the improvement of video download performance and video quality.

[1]  Zhuoqing Morley Mao,et al.  Internet Censorship in China: Where Does the Filtering Occur? , 2011, PAM.

[2]  Keith W. Ross,et al.  Topology Mapping and Geolocating for China's Internet , 2013, IEEE Transactions on Parallel and Distributed Systems.

[3]  I. Stoica,et al.  A case for a coordinated internet video control plane , 2012, CCRV.

[4]  J. Choi,et al.  Net Neutrality and Investment Incentives , 2008, SSRN Electronic Journal.

[5]  Paul Barford,et al.  Revisiting broadband performance , 2012, Internet Measurement Conference.

[6]  Ben Y. Zhao,et al.  Understanding user behavior in large-scale video-on-demand systems , 2006, EuroSys.

[7]  Vyas Sekar,et al.  Understanding the impact of video quality on user engagement , 2011, SIGCOMM.

[8]  Gaogang Xie,et al.  On the geographic patterns of a large-scale mobile video-on-demand system , 2014, IEEE INFOCOM 2014 - IEEE Conference on Computer Communications.

[9]  Nick Feamster,et al.  Helping users shop for ISPs with internet nutrition labels , 2011, HomeNets '11.

[10]  Nick Feamster,et al.  Broadband internet performance , 2011, SIGCOMM 2011.

[11]  Katerina J. Argyraki,et al.  Network neutrality inference , 2014, SIGCOMM.

[12]  Yi Sun,et al.  The case for P2P mobile video system over wireless broadband networks: A practical study of challenges for a mobile video provider , 2013, IEEE Network.

[13]  Boris Nechaev,et al.  Netalyzr: illuminating the edge network , 2010, IMC '10.

[14]  Minlan Yu,et al.  Tradeoffs in CDN designs for throughput oriented traffic , 2012, CoNEXT '12.

[15]  Gang Liu,et al.  Cloud download: using cloud utilities to achieve high-quality content distribution for unpopular videos , 2011, ACM Multimedia.

[16]  Bruce M. Maggs,et al.  Less pain, most of the gain: incrementally deployable ICN , 2013, SIGCOMM.

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

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

[19]  Gaogang Xie,et al.  Watching videos from everywhere: a study of the PPTV mobile VoD system , 2012, IMC '12.

[20]  Lusheng Ji,et al.  Understanding the impact of network dynamics on mobile video user engagement , 2014, SIGMETRICS '14.

[21]  Keith W. Ross,et al.  A Measurement Study of a Large-Scale P2P IPTV System , 2007, IEEE Transactions on Multimedia.

[22]  Srinivasan Seshan,et al.  Developing a predictive model of quality of experience for internet video , 2013, SIGCOMM.

[23]  Thomas Lumley,et al.  Kendall's advanced theory of statistics. Volume 2A: classical inference and the linear model. Alan Stuart, Keith Ord and Steven Arnold, Arnold, London, 1998, No. of pages: xiv+885. Price: £85.00. ISBN 0‐340‐66230‐1 , 2000 .

[24]  Ning Xia,et al.  Inside the bird's nest: measurements of large-scale live VoD from the 2008 olympics , 2009, IMC '09.

[25]  Yong Liu,et al.  Measurement and Modeling of Video Watching Time in a Large-Scale Internet Video-on-Demand System , 2013, IEEE Transactions on Multimedia.

[26]  Vyas Sekar,et al.  Improving fairness, efficiency, and stability in HTTP-based adaptive video streaming with FESTIVE , 2012, CoNEXT '12.

[27]  John P. Rula,et al.  Crowdsourcing ISP characterization to the network edge , 2011, W-MUST '11.

[28]  Cheng Huang,et al.  Challenges, design and analysis of a large-scale p2p-vod system , 2008, SIGCOMM '08.

[29]  Yi Sun,et al.  Mobile video popularity distributions and the potential of peer-assisted video delivery , 2013, IEEE Communications Magazine.

[30]  Bo Li,et al.  Design and deployment of a hybrid CDN-P2P system for live video streaming: experiences with LiveSky , 2009, ACM Multimedia.

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

[32]  David Clark,et al.  Understanding Broadband Speed Measurements , 2010 .

[33]  Srinivasan Seshan,et al.  Analyzing the potential benefits of CDN augmentation strategies for internet video workloads , 2013, Internet Measurement Conference.

[34]  K. K. Ramakrishnan,et al.  Over the top video: the gorilla in cellular networks , 2011, IMC '11.

[35]  Nick McKeown,et al.  Confused, timid, and unstable: picking a video streaming rate is hard , 2012, Internet Measurement Conference.