Skip to main content

A Multivariate Approach to Predicting Quantity of Failures in Broadband Networks Based on a Recurrent Neural Network

Journal of Network and Systems Management volume 24, pages 189–221 (2016)Cite this article

Abstract

In this paper, we present a multivariate recurrent neural network model for short-time prediction of the number of failures that are expected to be reported by users of a broadband telecommunication network. An accurate prediction of the expected number of reported failures is becoming increasingly important to service providers. It enables proactive actions and improves the decision-making process, operational network maintenance, and workforce allocation. Our previous studies have shown that the recursive neural network is flexible enough to approximate the dynamics of the failure reporting process. Development of the model is based on long-term monitoring of failure-reporting processes and experience gained through fault management related to the network of one of the leading Croatian telecom providers (T-HT). Many factors, both in the network and outside the network, influence the time series representing failure reporting. The model encompasses the most important predictor variables and their logical and temporal dependencies. Predictor variables represent internal factors such as profiles of past and current quantities of failures as well as external factors like weather forecasts or announced activities (scheduled maintenance) in the network. External factors have a strong effect on fault occurrence, which finally results in failures reported by users. These factors are quantified and included as input variables to our model. The model is fitted to the data from different sources like an error-logging database, a trouble-ticket archive, announced settings logs and a meteo-data archive. The accuracy of the model is examined on simulation tests varying the prediction horizons. Assessment of the model’s accuracy is made by comparing results obtained by prediction and the actual data. This research represents a real-world case study from telecom operations. The developed prediction model is scalable and adaptable so that other relevant input factors can be added as needed. Hence, the proposed prediction approach based on the model can be efficiently implemented as a functionality in real fault-management processes where a variety of available input data of different volumes exist.

This is a preview of subscription content, access via your institution.

Access options

Buy single article

Instant access to the full article PDF.

USD 39.95

Price includes VAT (USA)
Tax calculation will be finalised during checkout.

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12
Fig. 13
Fig. 14
Fig. 15
Fig. 16
Fig. 17
Fig. 18

Notes

  1. The range of values of this MTBF reduction factor has been published as a result of an internal technical analysis encompassing networks of 16 telecom operators in Western and Central Europe. The range (2–6) is quite large because of considerable differences in the equipment that is installed in the analyzed national networks and because of different efficiencies of the fault-repair systems and processes implemented.

References

  1. Avizienis, A., Laprie, J.-C.: Dependable computing: from concepts to design diversity. In: Proceedings of the IEEE (1986). doi:10.1109/PROC.1986.13527

  2. Melliar-Smith, P.M., Randell, B.: Software reliability: the role of programmed exception handling. In: Proceedings of the ACM Conference on Language Design for Reliable Software (1977). doi:10.1145/800022.808315

  3. Laprie, J.-C., Kanoun, K.: Software reliability and system reliability. In: Lyu, M.R. (ed.) Handbook of Software Reliability Engineering, chapter 2, pp. 27–69. McGraw-Hill, New York (1996)

    Google Scholar 

  4. Salfner, F., Lenk, M., Malek. M.: A survey of online failure prediction methods. J. ACM Comput. Surv. (2010). doi:10.1145/1670679.1670680

  5. A guide to standard and high-definition digital video measurements. Publishing Tektronix. http://www.tek.com/regional-page/guide-standard-hd-digital-video-measurements (2007). Accessed 15 August 2013

  6. Held, G.: Understanding IPTV (Informa Telecoms and Media). Auerbach publications, Boston (2006)

    Book  Google Scholar 

  7. Kandula, S., Katabi, D., Vasseur, J.P.: Shrink: A tool for failure diagnosis in IP networks. In: Proceedings of the ACM SIGCOMM Workshop on Mining Network Data (MineNet 2005), pp. 173–178. ACM (2005). doi:10.1145/1080173.1080178

  8. Mao, Y., Jamjoom, H., Tao, S., Smith, J.M.: Networkmd: topology inference and failure diagnosis in the last mile. In: Proceedings of the 7th ACM SIGCOMM Conference on Internet measurement (IMC 2007), pp. 189–202. ACM (2007), doi: 10.1145/1298306.1298333

  9. Kavulya, S.P., Joshi, K., Hiltunen, M., Daniels, S., Gandhi, R., Narasimhan, P.: Draco: Top-down statistical diagnosis of large-scale VoIP networks. Carnegie Mellon University, AT&T Labs-Research. http://www.pdl.cmu.edu/PDL-FTP/ProblemDiagnosis/CMU-PDL-11-109.pdf (2011)

  10. Mahimkar, A., Ge, Z., Shaikh, A., Wang, J., Yates, J., Zhang, Y., Zhao, Q.: Towards automated performance diagnosis in a large IPTV network. In: Proceedings of the ACM SIGCOMM 2009 conference on Data communication, pp. 231–242. ACM (2009). doi:10.1145/1592568.1592596

  11. Song, H.H., Ge, Z., Mahimkar, A., Wang, J., Yates, J., Zhang, Y.: Analyzing IPTV set-top box crashes. In: Proceedings of the 2nd ACM SIGCOMM Workshop on Home Networks (HomeNets 2011), pp. 31–36. ACM (2011). doi:10.1145/2018567.2018575

  12. Mahimkar, A., Song, H.H., Ge, Z., Shaikh, A., Wang, J., Yates, J., Zhang, Y., Emmons, J.: Detecting the performance impact of upgrades in large operational networks. In: Proceedings of the ACM SIGCOMM 2010 Conference, pp. 303–314. ACM (2010). doi:10.1145/1851182.1851219

  13. Guo, Z.X., Wong, W.K., Li, M.: A multivariate intelligent decision-making model for retail sales forecasting. Decis. Support Syst. 55, 247–255 (2013). doi:10.1016/j.dss.2013.01.026

    Article  Google Scholar 

  14. Soroush, A., Bahreininejad A., van den Berg, J.: A hybrid customer prediction system based on multiple forward stepwise logistic regression mode. Intell. Data Anal. 16, 265–278 (2012). doi:10.3233/IDA-2012-0523

  15. Mastorocostas, P., Hilas, C., Varsamis, D., Dova, S.: A recurrent neural network-based forecasting system for telecommunications call volume. Appl. Math. Inf. Sci. 7(5), 1643–1650 (2013). doi:10.12785/amis/070501

    Article  Google Scholar 

  16. Oduro-Gyimah, F.K., Azasoo, J.Q., Boateng, K.O.: Statistical analysis of outage time of commercial telecommunication networks in Ghana. In: Proceedings of the International Conference on Adaptive Science and Technology, pp 1–8 ICAST (2013). doi:10.1109/ICASTech.2013.6707520

  17. Jaudet, M., lqbal, N., Hussain, A., Sharif, K.: Temporal classification for fault-prediction in a real-world telecommunications network. In: Proceedings of the International Symposium on Emerging Technologies, pp. 209–214 IEEE (2005). doi:10.1109/ICET.2005.1558882

  18. Zhang, X., Sugiyama, A., Kitabayashi, H.: Estimating telecommunication equipment failures due to lightning surges by using population density. In: Proceedings of the International Conference on Quality and Reliability, pp. 182–185, ICQR (2011). doi:10.1109/ICQR.2011.6031705

  19. Barbosa, C., Ying, X., Day, P., Zeddam, A.: Recent progress of ITU-T recommendations on lightning protection. In: Proceedings of the 7th Asia-Pacific International Conference on Lighting (APL 2011), pp. 258–262. IEEE (2011). doi:10.1109/APL.2011.6110120

  20. Schulman, A., Spring. N.: Pingin’ in the rain. In: Proceedings of the ACM SIGCOMM Conference on Internet Measurement (IMC 2011), pp. 19–28. ACM (2011). doi:10.1145/2068816.2068819

  21. Jin, Y., Duffield, N., Gerber, A., Haffner, P., Sen, S., Zhang Z.: NEVERMIND, the problem is already fixed: Proactively detecting and troubleshooting customer DSL problems. In: Proceedings of the 6th International Conference (Co-NEXT ‘10), Artic. 7. ACM (2010). doi:10.1145/1921168.1921178

  22. Armstrong, J.S.: Principles of forecasting: a handbook for researchers and practitioners. Stanford University, Kluwer. http://www.gwern.net/docs/predictions/2001-principlesforecasting.pdf (2002)

  23. Deljac, Ž., Kunštić, M.: A comparison of methods for fault prediction in the broadband networks. In: Proceedings of the 18th International Conference on Software, Telecommunications and Computer Networks (SoftCOM 2010), pp. 42–46. IEEE (2010)

  24. Deljac, Ž., Kunštić, M., Spahija, B.: A comparison of traditional forecasting methods for short-term and long-term prediction of faults in the broadband networks. In: Proceedings of 34th international convention on information and communication technology, electronics and microelectronics (MIPRO 2011), pp. 517–522. IEEE (2011)

  25. Deljac, Ž., Kunštić, M., Spahija, B.: Using temporal neural networks to forecasting of broadband network faults. In: Proceedings of the 19th International Conference on Software, Telecommunications and Computer Networks (SoftCOM 2011), pp. 1–5. IEEE (2011)

  26. Demuth, H., Beale, M., Hagan, M.: Neural Network Toolbox™ 5. The MathWorks Inc., Natick (2006)

    Google Scholar 

  27. Coulibaly, P., Anctil, F., Bobee, B.: Multivariate reservoir inflow forecasting using temporal neural networks, pp. 367–376. J. Hydrol. Eng., ASCE (2001)

    Google Scholar 

  28. Dijk, O.E.: Analysis of recurrent neural networks with application to speaker independent phoneme recognition. University of Twente, Department of Electrical Engineering, pp. 21–24. http://www.eskodijk.nl/doc/Dijk99_Recurrent_Neural_Networks.pdf (1999)

  29. Dodds, E.D., Celaya, B.: Locating Water Ingress in Telephone Cables Using Frequency Domain Reflectometry. In: Proceedings of the Canadian Conference on Electrical and Computer Engineering, pp. 324–327. IEEE (2005). doi:10.1109/CCECE.2005.1556938

  30. Celaya, B., Dodds, E.D.: Single-ended DSL line tester. In: Proceedings of the Canadian Conference on Electrical and Computer Engineering, pp. 2155–2158. IEEE (2004). doi:10.1109/CCECE.2004.1347670

  31. Spahija, B., Deljac, Ž.: Proactive copper pair troubleshooting utilizing principal component analysis. In: Proceedings of the 18th International Conference on Software, Telecommunications and Computer Networks (SoftCOM 2010). IEEE (2010)

  32. Free Meteo Forecast Archive (2012) (Stations: Zagreb/Grič, Rijeka/Kozala and Split/Marjan). http://freemeteo.com.hr

Download references

Author information

Authors and Affiliations

  1. Technical Functions, T-Hrvatski Telekom (T-HT), Zagreb, Croatia

    Željko Deljac & Gordan Krčelić

  2. Faculty of Electrical Engineering and Computing, University of Zagreb, Zagreb, Croatia

    Mirko Randić

Authors
  1. Željko Deljac
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Mirko Randić
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Gordan Krčelić
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Željko Deljac.

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Deljac, Ž., Randić, M. & Krčelić, G. A Multivariate Approach to Predicting Quantity of Failures in Broadband Networks Based on a Recurrent Neural Network. J Netw Syst Manage 24, 189–221 (2016). https://doi.org/10.1007/s10922-015-9348-6

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10922-015-9348-6

Keywords

  • Proactive fault management
  • Failure reporting
  • Failure prediction
  • Predictor variables
  • Multivariate model
  • NARX
  • Telecommunication network