Improving quality of adaptive video by traffic prediction with (F)ARIMA models

During the past years, adaptive video based on hypertext transfer protocol HTTP has become very popular. Streaming of the adaptive video relies heavily on an estimation of end-to-end network throughput, which can be challenging especially in mobile networks, where the capacity highly fluctuates. In this work, we propose to predict the network throughput using its past measurements. As the analysis shows, the network throughput forms a long range-dependent process, thus, for the throughput prediction we apply fractional ARIMA (FARIMA) model. Our approach does not require any modifications to the network infrastructure or the TCP stack. The predictions are performed for data traces obtained from measurements of throughput of a real mobile network. As the experiment shows, the obtained traffic model is able to enhance the performance of an adaptive streaming algorithm. Compared to the throughput predictors employed in contemporary systems dedicated to adaptive video streaming, the proposed technique obtains better results when taking into account effectiveness of network capacity utilisation and stability of video play-out.

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

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

[3]  Nicola Bui,et al.  Modelling Throughput Prediction Errors as Gaussian Random Walks , 2014 .

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

[5]  Andreas Terzis,et al.  CQIC: Revisiting Cross-Layer Congestion Control for Cellular Networks , 2015, HotMobile.

[6]  Swarun Kumar,et al.  piStream: Physical Layer Informed Adaptive Video Streaming over LTE , 2015, MobiCom.

[7]  Yan Liu,et al.  On adaptive video streaming with predictable streaming performance , 2014, 2014 IEEE Global Communications Conference.

[8]  Rangarajan,et al.  Integrated approach to the assessment of long range correlation in time series data , 2000, Physical review. E, Statistical physics, plasmas, fluids, and related interdisciplinary topics.

[9]  Xin Jin,et al.  Can Accurate Predictions Improve Video Streaming in Cellular Networks? , 2015, HotMobile.

[10]  Jan Beran,et al.  Statistics for long-memory processes , 1994 .

[11]  K. Torre,et al.  Fractal analyses for 'short' time series: A re-assessment of classical methods , 2006 .

[12]  Hari Balakrishnan,et al.  Stochastic Forecasts Achieve High Throughput and Low Delay over Cellular Networks , 2013, NSDI.

[13]  Rémi Houdaille,et al.  Shaping HTTP adaptive streams for a better user experience , 2012, MMSys '12.

[14]  Aiko Pras,et al.  QoE-driven in-network optimization for Adaptive Video Streaming based on packet sampling measurements , 2015, Comput. Networks.

[15]  Thomas Stockhammer,et al.  Dynamic adaptive streaming over HTTP --: standards and design principles , 2011, MMSys.

[16]  Ali C. Begen,et al.  Probe and Adapt: Rate Adaptation for HTTP Video Streaming At Scale , 2013, IEEE Journal on Selected Areas in Communications.

[17]  Adam Wolisz,et al.  Low-Delay Adaptive Video Streaming Based on Short-Term TCP Throughput Prediction , 2015, ArXiv.

[18]  Arkadiusz Biernacki,et al.  Analysis and modelling of traffic produced by adaptive HTTP-based video , 2017, Multimedia Tools and Applications.

[19]  Nick McKeown,et al.  Using the Buffer to Avoid Rebuffers: Evidence from a Large Video Streaming Service , 2014, ArXiv.

[20]  Christian Timmerer,et al.  An evaluation of dynamic adaptive streaming over HTTP in vehicular environments , 2012, MoVid '12.

[21]  Peter Dalgaard,et al.  R Development Core Team (2010): R: A language and environment for statistical computing , 2010 .

[22]  Sophia Daskalaki,et al.  Comparing forecasting approaches for Internet traffic , 2015, Expert Syst. Appl..

[23]  Filip De Turck,et al.  On the merits of SVC-based HTTP Adaptive Streaming , 2013, 2013 IFIP/IEEE International Symposium on Integrated Network Management (IM 2013).

[24]  D. G. Wakde,et al.  On the prediction of packet process in network traffic using FARIMA time-series model , 2013 .

[25]  Christian Timmerer,et al.  Dynamic adaptive streaming over HTTP dataset , 2012, MMSys '12.

[26]  Rajnish K. Yadav,et al.  Comparative evaluation of ARIMA and ANFIS for modeling of wireless network traffic time series , 2014, EURASIP J. Wirel. Commun. Netw..

[27]  Carsten Griwodz,et al.  Fine-grained scalable streaming from coarse-grained videos , 2009, NOSSDAV '09.

[28]  Nick McKeown,et al.  Downton abbey without the hiccups: buffer-based rate adaptation for HTTP video streaming , 2013, FhMN@SIGCOMM.

[29]  Christian Timmerer,et al.  A VLC media player plugin enabling dynamic adaptive streaming over HTTP , 2011, ACM Multimedia.

[30]  Bruno Sinopoli,et al.  A Control-Theoretic Approach for Dynamic Adaptive Video Streaming over HTTP , 2015, Comput. Commun. Rev..

[31]  Adam Wolisz,et al.  Adaptation algorithm for adaptive streaming over HTTP , 2012, 2012 19th International Packet Video Workshop (PV).

[32]  Irene A. Stegun,et al.  Handbook of Mathematical Functions. , 1966 .

[33]  Phuoc Tran-Gia,et al.  Using buffered playtime for QoE-oriented resource management of YouTube video streaming , 2013, Trans. Emerg. Telecommun. Technol..

[34]  Aggelos Lazaris,et al.  Modeling multiplexed traffic from H.264/AVC videoconference streams , 2010, Comput. Commun..

[35]  Qiang Xu,et al.  PROTEUS: network performance forecast for real-time, interactive mobile applications , 2013, MobiSys '13.