Abstract
Due to recent developments in Over-The-Top (OTT) technologies, Pay-TV operators have begun a migration process of managed IP Television (IPTV) services to more appealing OTT approaches. In these scenarios, being able to predict when and what resources will be necessary at any given point is crucial to a high-quality, efficient, and cost-effective operation, especially when dealing with the dynamic and resource-intensive requirements of IPTV multimedia services. To evaluate the advantages of demand forecasting for efficient Catch-up TV delivery on OTT scenarios, this research work explores several classes of machine learning models regarding their accuracy, computational requirement trade-offs, and deployability. The training process relies on a dataset comprised of Catch-up TV usage logs acquired from an IPTV operator’s live production service containing over 1 million subscribers. A predictive and dynamic resource provisioning approach is proposed and evaluated in terms of bandwidth and storage savings. Results demonstrate that forecasting Catch-up TV demand is practical, suitable for integration in OTT solutions, and useful in improving efficiency, with benefits to operators and consumers. Significant savings in bandwidth and storage are shown to be achievable, enabling green and cost-effective resource usage.
Similar content being viewed by others
References
Aguado A, Davis M, Peng S, Alvarez MV, Lopez V, Szyrkowiec T, Autenrieth A, Vilalta R, Mayoral A, Munoz R, Casellas R, Martinez R, Yoshikane N, Tsuritani T, Nejabati R, Simeonidou D (2016) Dynamic virtual network reconfiguration over SDN orchestrated multitechnology optical transport domains. J Light Technol 34(8):1933–1938. doi:10.1109/JLT.2016.2522823
ANACOM (2015) Subscription television service statistical information 2nd quarter 2015. Tech. rep., ANACOM. http://www.anacom.pt/streaming/STVS2quarter2015.pdf?contentId=1366508&field=ATTACHED_FILE. Accessed: 12-2015
Bahrpeyma F, Haghighi H, Zakerolhosseini A (2015) An adaptive RL based approach for dynamic resource provisioning in Cloud virtualized data centers. Computing 97(12):1209–1234. doi:10.1007/s00607-015-0455-8
Beauvisage T, Beuscart JS (2012) Audience dynamics of online catch up TV. In: Proceedings of the 21st international conference companion on world wide web - WWW ’12 companion. doi:10.1145/2187980.2188077. ACM Press, New York, USA, p 461
Burden F, Winkler D (2009) Bayesian regularization of neural networks. In: Livingstone DJ (ed) Artificial neural networks, methods in molecular biology. doi:10.1007/978-1-60327-101-1_3, vol 458. Humana Press, pp 23–42
Calin D, Schulzrinne H (2015) Intelligent content delivery over wireless via SDN. In: 2015 IEEE wireless communications and networking conference (WCNC). doi:10.1109/WCNC.2015.7127806, pp 2185–2190
Caruana R, Niculescu-Mizil A, Crew G, Ksikes A (2004) Ensemble selection from libraries of models. In: Twenty-first international conference on machine learning - ICML ’04. doi:10.1145/1015330.1015432, vol 34. ACM Press, New York, p 18
Dhotre IA (2009) Operating systems, eighth edn. Technical Publications. https://books.google.pt/books?id=iQzqVqFz3IsC
Famaey J, Iterbeke F, Wauters T, De Turck F (2013) Towards a predictive cache replacement strategy for multimedia content. J Netw Comput Appl 36(1):219–227. doi:10.1016/j.jnca.2012.08.014
Harstead E, Sharpe R (2015) Forecasting of access network bandwidth demands for aggregated subscribers using Monte Carlo methods. IEEE Commun Mag 53(3):199–207. doi:10.1109/MCOM.2015.7060505
Hyndman R (2006) Another look at forecast-accuracy metrics for intermittent demand. Foresight: The International Journal of Applied Forecasting (4):43–46. http://www.researchgate.net/publication/5055536_Another_Look_at_Forecast_Accuracy_Metrics_for_Intermittent_Demand/file/d912f50ff0c2ad9136.pdf. Accessed: 01-2016
Hyndman RJ (2015) Forecast: forecasting functions for time series and linear models. https://cran.r-project.org/web/packages/forecast/index.html. Accessed: 01-2016
John GH, Kohavi R, Pfleger K (1994) Irrelevant features and the subset selection problem. In: Cohen WW, Hirsh H (eds) Machine learning: Proceedings of the eleventh international conference. http://machine-learning.martinsewell.com/feature-selection/JohnKohaviPfleger1994.pdf. Accessed: 09-2015. Morgan Kaufmann, San Francisco, pp 121–129
Karatzoglou A, Smola A, Hornik K (2015) Kernlab. https://cran.r-project.org/web/packages/kernlab/kernlab.pdf. Accessed: 09-2015
Karsoliya S (2012) Approximating number of hidden layer neurons in multiple hidden layer BPNN architecture. International Journal of Engineering Trends and Technology (IJETT) 3(6):714–717. http://www.ijettjournal.com/volume-3/issue-6/IJETT-V3I6P206.pdf
Kephart J, Chess D (2003) The vision of autonomic computing. Computer 36(1):41–50. doi:10.1109/MC.2003.1160055
Kryftis Y, Mastorakis G, Mavromoustakis CX, Batalla JM, Pallis E, Kormentzas G (2016) Efficient entertainment services provision over a novel network architecture. IEEE Wirel Commun 23(1):14–21. doi:10.1109/MWC.2016.7422401
Kuhn M (2008) Building predictive models in r using the caret package. J Stat Softw 28(5):1–26. http://www.jstatsoft.org/v28/i05. Accessed: 09-2015
Kuhn M (2015) caret. https://cran.r-project.org/web/packages/caret/caret.pdf. Accessed: 09-2015
Kuhn M, Johnson K (2013) Applied predictive modeling. Springer, New York. doi:10.1007/978-1-4614-6849-3
Liaw A (2015) randomForest. https://cran.r-project.org/web/packages/randomForest/randomForest.pdf. Accessed: 09-2015
Mercian A, McGarry MP, Reisslein M, Kellerer W (2015) Software defined optical access networks (SDOANs): a comprehensive survey. IEEE Commun Surv Tutorials 18:1–23. doi:10.1109/COMST.2016.2586999
Mevik BH, Wehrens R, Liland KH (2015) Pls. https://cran.r-project.org/web/packages/pls/pls.pdf. Accessed: 09-2015
Molinaro AM, Simon R, Pfeiffer RM (2005) Prediction error estimation: a comparison of resampling methods. Bioinformatics 21 (15):3301–3307. doi:10.1093/bioinformatics/bti499
Nencioni G, Sastry N, Chandaria J, Crowcroft J (2013) Understanding and decreasing the network footprint of catch-up tv. In: Proceedings of the 22nd international conference on world wide web - WWW ’13. doi:10.1145/2488388.2488472. ACM Press, New York, pp 965–976
Nielsen (2014) The digital consumer. http://www.nielsen.com/content/dam/corporate/us/en/reports-downloads/2014Reports/the-digital-consumer-report-feb-2014.pdf. Accessed: 09-2015
Nogueira J, Gonzalez D, Guardalben L, Sargento S (2016) Over-the-top catch-up TV content-aware caching. In: 21st IEEE symposium on computers and communication (ISCC). Messina, Italy, p 6
Nogueira J, Guardalben L, Cardoso B, Sargento S (2016) Catch-up TV analytics: statistical characterization and consumption patterns identification on a production service. Multimedia Systems 1–19. doi:10.1007/s00530-016-0516-7
Pathan M, Buyya R (2008) A taxonomy of CDNs. In: Content delivery networks, chap. a taxonomy. doi:10.1007/978-3-540-77887-5_2. Springer, Berlin, Heidelberg, pp 33–77
R Foundation for Statistical Computing (2016) The R project for statistical computing. https://www.r-project.org/. Accessed: 01-2016
Ranjan R, Benatallah B, Dustdar S, Papazoglou MP (2015) Cloud resource orchestration programming: overview, issues, and directions. IEEE Internet Comput 19 (5):46–56. doi:10.1109/MIC.2015.20
Ripley B, Venables W (2015) Class. https://cran.r-project.org/web/packages/class/class.pdf. Accessed: 09-2015
Rodriguez PP, Gianola D (2015) Brnn (Bayesian regularization for feed-forward neural networks). https://cran.r-project.org/web/packages/brnn/brnn.pdf. Accessed: 01-2016
RStudio Inc. (2016) RSTudio. https://www.rstudio.com/. Accessed: 01-2016
Saeys Y, Inza IN, Larranaga P (2007) A review of feature selection techniques in bioinformatics. Bioinformatics 23(19):2507–2517. doi:10.1093/bioinformatics/btm344
Szlek J, Mendyk A (2015) Fscaret. https://cran.r-project.org/web/packages/fscaret/fscaret.pdf. Accessed: 09-2015
Tofallis C (2015) A better measure of relative prediction accuracy for model selection and model estimation. J Oper Res Soc 66(8):1352–1362. doi:10.1057/jors.2014.103. Accessed: 01-2016
Vanattenhoven J, Geerts D (2015) Broadcast, video-on-demand, and other ways to watch television content. In: Proceedings of the ACM international conference on interactive experiences for TV and online video - TVX ’15. doi:10.1145/2745197.2745208. ACM Press, New York, pp 73–82
Weingärtner R, Bräscher GB, Westphall CB (2015) Cloud resource management: a survey on forecasting and profiling models. J Netw Comput Appl 47:99–106. doi:10.1016/j.jnca.2014.09.018
Wirth R (2000) CRISP-DM: towards a standard process model for data mining. In: Proceedings of the fourth international conference on the practical application of knowledge discovery and data mining. http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.198.5133. Accessed: 12-2015, pp 29–39
Yeo IK, Johnson RA (2000) A new family of power transformations to improve normality or symmetry. Biometrika 87(4):954–959. doi:10.1093/biomet/87.4.954
Acknowledgements
The authors would like to thank Fausto Carvalho (Altice Labs, SA) and João Ferreira (MEO - Serviços de Comunicações e Multimédia, SA) for the key discussions and for providing the raw Catch-up TV dataset.
This research was funded by UltraTV (Portugal 2020 POCI-01-0247-FEDER-017738), by FCT/MEC through national funds, and when applicable co-funded by FEDER – PT2020 partnership agreement under the project UID/EEA/50008/2013 OT2Delivery (Over-the-top Multimedia Content Delivery for Next Generation Mobile Networks).
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Nogueira, J., Guardalben, L., Cardoso, B. et al. Catch-up TV forecasting: enabling next-generation over-the-top multimedia TV services. Multimed Tools Appl 77, 14527–14555 (2018). https://doi.org/10.1007/s11042-017-5043-9
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-017-5043-9