A Model Sensitive to Adaptation for Quality Prediction of Experience in Internet Videos
Abstract
Live video streams have already broken the boundary of the global scale and now face a new challenge: delivering uniform high quality of experience (QoE) to all their customers. To address this issue, several approaches use historical performance-related information to infer the quality of experience (QoE) of their future sessions. This allows the resources needed for each type of client to be better estimated even before the session starts. However, the success of such schemes depends on an accurate QoE prediction: Previous studies use performance metrics such as interrupt rate and average bitrate and achieve 70% prediction accuracy. In the present work we present a new approach, which correlates the customer QoE with its bitrate adaptation flow. We have shown that this set of metrics provides a forecast accuracy of 81%. We also presented a case study for customer allocation using the predictor and found a potential for increasing overall QoE compared to standard allocation.
References
Balachandran, A., Sekar, V., Akella, A., Seshan, S., Stoica, I., and Zhang, H. (2013). Developing a predictive model of quality of experience for internet video. SIGCOMM Comput. Commun. Rev., 43(4):339–350.
Breiman, L., Friedman, J., Olshen, R., and Stone, C. (1984). Classification and Regression Trees. Wadsworth and Brooks, Monterey, CA.
da Costa Filho, R. I. T., Lautenschlager, W., Kagami, N., Roesler, V., and Gaspary, L. P. (2016). Network fortune cookie: Using network measurements to predict video streaming performance and qoe. In 2016 IEEE Global Communications Conference (GLOBECOM), pages 1–6.
Dobrian, F., Sekar, V., Awan, A., Stoica, I., Joseph, D., Ganjam, A., Zhan, J., and Zhang, H. (2011). Understanding the impact of video quality on user engagement. In Proceedings of the ACM SIGCOMM 2011 Conference, SIGCOMM ’11.
Guarnieri, T., ´Italo Cunha, Almeida, J., Drago, I., and Vieira, A. B. (2017). Characterizing QoE in large-scale live streaming. In Proc. of the IEEE GLOBECOM.
Ho, T. K. (1998). The random subspace method for constructing decision forests. IEEE Transactions on Pattern Analysis and Machine Intelligence, 20(8):832–844.
Jiang, J., Sun, S., Sekar, V., and Zhang, H. (2017). Pytheas: Enabling data-driven quality of experience optimization using group-based exploration-exploitation. In 14th USENIX Symposium on Networked Systems Design and Implementation (NSDI 17), pages 393–406, Boston, MA. USENIX Association.
Krishnan, S. S. and Sitaraman, R. K. (2013). Video stream quality impacts viewer behavior: Inferring causality using quasi-experimental designs. IEEE/ACM Transactions on Networking, 21(6):2001–2014.
Liu, X., Dobrian, F., Milner, H., Jiang, J., Sekar, V., Stoica, I., and Zhang, H. (2012). A case for a coordinated internet video control plane. ACM SIGCOMM Computer Communication Review, 42.
Mao, H., Netravali, R., and Alizadeh, M. (2017). Neural adaptive video streaming with pensieve. In Proceedings of the Conference of the ACM Special Interest Group on Data Communication, SIGCOMM ’17, pages 197–210.
Norris, J. R. (1998). Markov chains. Cambridge series in statistical and probabilistic mathematics. Cambridge University Press.
Seufert, M., Egger, S., Slanina, M., Zinner, T., Hoßfeld, T., and Tran-Gia, P. (2015). A survey on quality of experience of http adaptive streaming. IEEE Communications Surveys Tutorials, 17(1):469–492.
Sun, Y., Yin, X., Jiang, J., Sekar, V., Lin, F., Wang, N., Liu, T., and Sinopoli, B. (2016). Cs2p: Improving video bitrate selection and adaptation with data-driven throughput prediction. In Proceedings of the 2016 ACM SIGCOMM Conference, SIGCOMM ’16, pages 272–285. ACM.
