Advertisement

A Lightweight Prediction Method for Scalable Analytics of Multi-seasonal KPIs

  • Roberto Bruschi
  • Giuseppe Burgarella
  • Paolo LagoEmail author
Conference paper
Part of the Communications in Computer and Information Science book series (CCIS, volume 766)

Abstract

This paper presents an innovative prediction method for key performance indexes with multiple seasonal profiles. The proposed method, called Multiplicative Multi-Seasonal Model (MSMM) relies on a time series decomposition including multiple multiplicative seasonal profiles and a trend component. The method and its underlying model have been specifically designed to be computationally lightweight to scale to big-data scenarios envisaged in upcoming 5G-NFV environments. The MSMM performance has been evaluated on KPI traces of real operating infrastructures/services, made available by Yahoo! The obtained results outlined how the MSMM prediction method provides more accurate forest than well-known algorithm like the seasonal version of ARIMA, with much reduced computational weight.

Keywords

Predictive model Seasonal time series 5G NFV 

Notes

Acknowledgment

This work was supported by the INPUT (In-Network Programmability for next-generation personal cloUd service supporT) project, funded by the European Commission under the Horizon 2020 Programme (Grant no. 644672).

References

  1. 1.
    Chiosi, M., et al.: Network Functions Virtualization: An Introduction, Benefits, Enablers, Challenges & Call For Action, ETSI White Paper, October 2012. http://portal.etsi.org/NFV/NFV_White_Paper.pdf
  2. 2.
    Matsubara, D., Egawa, T., Nishinaga, N., Kafle, V.P., Shin, M.-K., Galis, A.: Toward future networks: a viewpoint from ITU-T. IEEE Commun. Mag. 51(3), 112–118 (2013)CrossRefGoogle Scholar
  3. 3.
    Corcoran, P.M.: Cloud computing and consumer electronics: a perfect match or a hidden storm? IEEE Consum. Electron. Mag. 1(2), 14–19 (2012)CrossRefGoogle Scholar
  4. 4.
    Matsubara, D., Egawa, T., Nishinaga, N., Kafle, V.P., Shin, M.-K., Galis, A.: Toward future networks: a viewpoint from ITU-T. IEEE Commun. Mag. 51(3), 112–118 (2013)CrossRefGoogle Scholar
  5. 5.
    Peng, M., Li, Y., Zhao, Z., Wang, C.: System architecture and key technologies for 5G heterogeneous cloud radio access networks. IEEE Netw. 29(2), 6–14 (2015)CrossRefGoogle Scholar
  6. 6.
    Matias, J., Garay, J., Toledo, N., Unzilla, J., Jacob, E.: Toward an SDN-enabled NFV architecture. IEEE Commun. Mag. 53(4), 187–193 (2015)CrossRefGoogle Scholar
  7. 7.
    Szabo, R., Kind, M., Westphal, F.J., Woesner, H., Jocha, D., Csaszar, A.: Elastic network functions: opportunities and challenges. IEEE Netw. 29(3), 15–21 (2015)CrossRefGoogle Scholar
  8. 8.
    Hawilo, H., Shami, A., Mirahmadi, M., Asal, R.: NFV: state of the art, challenges, and implementation in next generation mobile networks (vEPC). IEEE Netw. 28(6), 18–26 (2014)CrossRefGoogle Scholar
  9. 9.
    ETSI Network Function Virtualization Management and Orchestration Working Group (NFV MANO WG). http://portal.etsi.org/tb.aspx?tbid=796&SubTB=796
  10. 10.
    Clayman, S., Maini, E., Galis, A., Manzalini, A., Mazzocca, N.: The dynamic placement of virtual network functions. In: Proceedings of the 2014 IEEE Network Operations and Management Symposium (NOMS), Krakow, pp. 1–9 (2014)Google Scholar
  11. 11.
    Sun, X., Ansari, N., Wang, R.: Optimizing resource utilization of a data center. IEEE Comm. Surv. Tutor. 18(4), 2822–2846 (2016)CrossRefGoogle Scholar
  12. 12.
    Katris, C., Daskalaki, S.: Comparing forecasting approaches for internet traffic. Expert Syst. Appl. 42(21), 8172–8183 (2015). Elsevier, ISSN 0957-4174CrossRefzbMATHGoogle Scholar
  13. 13.
    Dalmazo, B.L., Vilela, J.P., Curado, M.: Performance analysis of network traffic predictors in the cloud. J. Netw. Syst. Manage. 25(2), 290–320 (2017)CrossRefGoogle Scholar
  14. 14.
    Feng, H., Shu, Y.: Study on network traffic prediction techniques. In: Proceedings of the 2005 International Conference on Wireless Communication Network and Mobile Computing, pp. 1041–1044 (2005)Google Scholar
  15. 15.
    Koehler, A.B., Snyder, R.D., Keith Ord, J.: Forecasting models and prediction intervals for the multiplicative Holt-Winters method. Int. J. Forecast. 17(2), 269–286 (2001)CrossRefGoogle Scholar
  16. 16.
    Fox, A.J.: Outliers in time series. J. R. Stat. Soc. Ser. B (Methodological) 34(3), 350–363 (1972)MathSciNetzbMATHGoogle Scholar
  17. 17.
    Gupta, M., Gao, J., Aggarwal, C.C., Han, J.: Outlier detection for temporal data: a survey. IEEE Trans. Knowl. Data Eng. 25(1), 1–20 (2013)CrossRefGoogle Scholar
  18. 18.
    Williams, A.W., Pertet, S.M., Narasimhan, P.: Tiresias: black-box failure prediction in distributed systems. In: Proceedings of the 21st International Parallel and Distributed Processing Symposium (IPDPS 2007), Long Beach, CA, USA, March 2007, pp. 1–8 (2007)Google Scholar
  19. 19.
    Vlachos, M., Yu, P., Castelli, V.: On periodicity detection and structural periodic similarity. In: Proceedings of the 5th SIAM International Conference on Data Mining (SDM 2005), Newport Beach, CA, USA, April 2005, pp. 449–460 (2005). ISBN:0898715938Google Scholar
  20. 20.
    Brockwell, P.J., Davis, R.A.: Nonstationary and seasonal time series models. In: Brockwell P.J., Davis R.A. (eds.) Introduction to Time Series and Forecasting. Springer Texts in Statistics. Springer, New York (2002). doi: 10.1007/0-387-21657-X_6, ISBN 0-387-95351-5
  21. 21.
    Hyndman, R.J., Athanasopoulos, G.: Forecasting: Principles and Practice. OTexts Ed., Heathmont (2016). Sect. 8.8, ISBN: 978-0987507105Google Scholar
  22. 22.
    Chatfield, C., Yar, M.: Prediction intervals for multiplicative Holt-Winters. Int. J. Forecast. 7(1), 31–37 (1991). Elsevier, ISSN 0169-2070CrossRefGoogle Scholar
  23. 23.
    Laptev, N., Amizadeh, A., Billawala, Y.: Yahoo labs news: announcing a benchmark dataset for time series anomaly detection, March 2015. http://labs.yahoo.com/news/announcing-a-benchmark-datasetfor-time-series-anomaly-detection

Copyright information

© Springer International Publishing AG 2017

Authors and Affiliations

  • Roberto Bruschi
    • 1
  • Giuseppe Burgarella
    • 2
  • Paolo Lago
    • 1
    • 3
    Email author
  1. 1.S3ITI National LabCNITGenoaItaly
  2. 2.Ericsson Telecomunicazioni S.p.A.GenoaItaly
  3. 3.DITENUniversity of GenoaGenoaItaly

Personalised recommendations