Probabilistic User Behavior Models
ICDM '03 Proceedings of the Third IEEE International Conference on Data Mining
Theory, Volume 1, Queueing Systems
Theory, Volume 1, Queueing Systems
Enabling DVD-like features in P2P video-on-demand systems
Proceedings of the 2007 workshop on Peer-to-peer streaming and IP-TV
Peer assisted VoD for set-top box based IP network
Proceedings of the 2007 workshop on Peer-to-peer streaming and IP-TV
Modeling user activities in a large IPTV system
Proceedings of the 9th ACM SIGCOMM conference on Internet measurement conference
A Measurement Study of a Large-Scale P2P IPTV System
IEEE Transactions on Multimedia
Inferring the QoE of HTTP video streaming from user-viewing activities
Proceedings of the first ACM SIGCOMM workshop on Measurements up the stack
Understanding couch potatoes: measurement and modeling of interactive usage of IPTV at large scale
Proceedings of the 2011 ACM SIGCOMM conference on Internet measurement conference
Modeling digital interactive TV users behavior
Proceedings of the 19th Brazilian symposium on Multimedia and the web
| Hi-index | 0.00 |
We investigate the user viewing activity for broadcast TV, pre-recorded content using Digital Video Recording (DVR) and video on demand (VoD) in an IP-based content distribution environment. Advanced stream control functions (play, pause, skip, rewind, etc.) provide users with a high level of interactivity, but place demands on the distribution infrastructure (servers, network, home-network) that can be difficult to manage at large scale. To support system design as well as network capacity planning, it is necessary to have a good model of user interaction. Using traces from a well-provisioned operational environment with a large user population, we first characterize interactivity for broadcast TV, DVR and VoD. We then develop parametric models of individual users stream control operations for VoD. Our analysis shows that interactive behavior is adequately characterized by two semi-Markov models, one for weekdays and another for weekends. We propose a parametric model for the underlying sojourn time distributions and show that it results in a superior fit compared to well known distributions (generalized Pareto and Weibull). In order to validate that our models faithfully capture user behavior, we compare the workload that a VoD server experiences in response to actual traces and synthetic data generated from our proposed models.