Abstract
Video services on the Internet are not able to offer consistent and assured performance to users or third-party applications. Measuring levels of performance over time is difficult, and obtaining accurate measures in real time is problematic; thus, reactive measures to address loss of performance are also problematic. The ability to predict service performance can be viewed as an important added-value, one that can help users or third-part applications select the proper online service provider. With this aim in view, we have designed a measurement system and deployed it in eleven provinces and cities in China to monitor two popular websites, Youku and Tudou. The analysis indicates that the performance trend of these two service providers followed daily changing patterns, such as rush hour traffic and lower service workloads at midnight; this is consistent with user behaviors. It was also confirmed that the future performance was related to the historical records. Based on these findings, we have decided to investigate the use of modified time series models to forecast the performance of such video services. Meanwhile, some machine learning models are implemented and compared as baseline models, such as Artificial Neural Network, Support Vector Machine, and Decision Tree. In addition, a hybrid model, which is generated by combining different machine learning models, is also studied as the baseline. An investigation shows that time series models are much more suitable to this prediction problem than baseline models in most situations. To alleviate the data sparseness problem in training the predictor, a new predictor that combines different information sources is proposed, thus improving prediction precision. Furthermore, the predictor is quite stable, and we have discovered that the average performance estimation is more accurate if the model is updated within 2–3 days, which is useful in some applications, e.g., video source analysis and recommendation systems.
Similar content being viewed by others
References
Adhikari R, Agrawal RK (2012) Combining multiple time series models through a robust weighted mechanism. First Int Conf Recent Adv Inf Technol 2012
Adhikari VK, Guo Y, Hao F et al (2012) Unreeling Netflix: understanding and improving multi-CDN movie delivery. INFOCOM 2012:1620–1628
Adhikari VK et al (2015) Measurement study of Netflix, Hulu, and a tale of three CDNs. IEEE/ACM Trans Networking 23(6):1984–1997
Ameigeiras P, Ramos-Munoz JJ, Navarro-Ortiz J, Lopez-Soler JM (2012) Analysis and modeling of YouTube traffic. Trans Emerg Telecommun Technol 23(4):360–377
Anand NC, Scoglio C, Natarajan B (2008) GARCH-non-linear time series model for traffic modeling and prediction. Netw Oper Manag Symp 2008:694–697
Artero JP (2010) Online video business models: YouTube vs. Hulu Palabra Clave 13(1):111–123
Attenberg J, Pandey S, Suel T (2009) Modeling and predicting user behavior in sponsored search. SIGKDDACM 2009:1067–1076
Balachandran A, Sekar V, Aditya A et al (2013) Developing a predictive model of quality of experience for internet video. SIGCOMM 43(4):339–350
Chabaa S, Zeroual A, Antari J (2010) Identification and prediction ofinternet traffic using artificial neural networks. J Intell Learn Syst Appl 2:147–155
Cheung YW, Lai KS (1995) Practitioner’s corner: lag order and critical values of a modified dickey-fuller test. Oxf Bull Econ Stat 57(3):411–419
Cortez P, Rio M, Rocha M, Sousa P (2006) Internet traffic forecasting using neural networks. Inter Joint Conf Neural Netw 2006:2635–2642
Eviews (2017) http://www.eviews.com/
Hoong NK, Hoong PK, Tan IKT, Muthuvelu N, Seng LC (2011) Impact of utilizing forecasted network traffic for data transfers. Int Conf Adv Commun Techonol 2011:1199–1204
Hoong PK, Tan IKT, Keong CY (2012) Bittorrent network traffic forecasting with ARMA. Int J Comput Netw Commun (IJCNC) 4(4):143–156
Iqbal MF, John LK (2012) Power and performance analysis of network traffic prediction techniques. IEEE Int Symp Perform Anal Syst Softw (ISPASS) 2012:112–113
Jiang Y, Wang Y, Feng R, Xue X, Zheng Y, Yang H (2013) Understanding and predicting interestingness of videos. Proceedings of the Twenty-Seventh AAAI Conference on Artificial Intelligence 2013: 1113–1119
Joshi M, Hadi TH (2015) A review of network traffic analysis and prediction techniques.arXiv:1507.05722
Radinsky K, Svore K, Dumais S et al. (2012) Modeling and predicting behavioral dynamics on the web. WWW 2012, pp 599–608
Shu Y, Yu M, Liu J, etc. (2003) Wireless traffic modeling and prediction using seasonal ARIMA models. ICC.2003
Sivakumar R, Ashok Kumar E, Sivaradje G (2011) Prediction of traffic load in wireless network using time series model. PACC 2011
Vujicic B, Chen H, Trajkovic L (2006) Prediction of traffic in a public safety network. IEEE Int Symp Circuits Syst 2006
Wang YA, Huang C, Li J, Ross KW (2011) Estimating the performance of hypothetical cloud service deployments: a measurement-based approach. INFOCOM 2011:2372–2380
Xu Q, Mehrotra S, Mao ZQ, Li J (2013) PROTEUS: network performance forecast for real-time, interactive mobile applications. Mob Syst 2013:347–360
Yu Y, Wang J, Song M, Song J (2010) Network traffic prediction and result analysis based on seasonal ARIMA and correlation coefficient. Int Conf Intell Syst Des Eng Appl 2010:980–983
Zeng D, Xu J, Gu J, etc. (2008) Short term traffic flow prediction using hybrid ARIMA and ANN models. Workshop Power Electron Intell Transportation Syst 2008, pp 621–625
Zhao H (2009) Multiscale analysis and prediction of network traffic. IPCCC 2009:388–393
Zhou B, He D, Sun Z (2006) Traffic predictability based on ARIMA/GARCH model. Next Generation Internet 2006:200–207
Acknowledgements
This work is supported by “Research of smart TV platform and service support environment” (XDA06040501) and “Youth Innovation Promotion Association of the Chinese Academy of Sciences” (Y529111601).
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
You, J., Xue, H., Gao, L. et al. Predicting the online performance of video service providers on the internet. Multimed Tools Appl 76, 19017–19038 (2017). https://doi.org/10.1007/s11042-017-4460-0
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-017-4460-0