Root Cause Analysis for Self-organizing Cellular Network: an Active Learning Approach

Abstract

To ease the configuration and maintenance of complex cellular networks, the self-organizing network (SON) is introduced. SON contains three major sub-functional groups: self-configuration, self-optimization, and self-healing. Among these, fault diagnosis in self-healing is crucial, and it is usually considered as a classification problem which is commonly addressed by supervised machine learning methods. However, the barrier to these methods is the difficulty in obtaining sufficient network fault data with label (fault cause). To achieve an effective classifier and dramatically reduce the number of labeled instances needed, we propose an active learning based fault diagnosis scheme, which can select unlabeled instances for labeling actively. According to the selection criteria, there are several query strategies. In this paper, we apply uncertainty sampling as the query strategy due to its low computational cost and high efficiency. Besides, we implement random sampling as a contrast which is a nonactive learning method. To verify the effectiveness of the proposed scheme, we construct a long term evolution (LTE) system level simulator by Network Simulator 3. Then several fault scenarios are simulated, and the records of key performance indicators with fault causes are collected. Extensive experiments demonstrate that the proposed scheme is effective in reducing the number of labeled instances needed, and it is also valid in the class-imbalanced data. Specifically, to achieve a classifier with an accuracy of 99%, the active learning based method only needs 74 labeled instances but the nonactive learning method needs 1354 ones.

This is a preview of subscription content, log in to check access.

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5

References

  1. 1.

    Chernogorov F, Repo I, Räisänen V, Nihtilä T, Kurjenniemi J (2015) Cognitive self-healing system for future mobile networks. 2015 International wireless communications and mobile computing conference (IWCMC), Dubrovnik, pp 628–633

    Google Scholar 

  2. 2.

    Gómez-Andrades A, Muñoz P, Khatib EJ, de-la-Bandera I, Serrano I, Barco R (2016) Methodology for the design and evaluation of self-healing LTE networks. IEEE Trans Veh Technol 65(8):6468–6486

    Article  Google Scholar 

  3. 3.

    Khatib E J, Barco R, Gómez-Andrades A, Serrano I (2016) Diagnosis based on genetic fuzzy algorithms for LTE self-healing. IEEE Trans Veh Technol 65(3):1639–1651

    Article  Google Scholar 

  4. 4.

    Sun M, Qian H, Zhu K, Guan D, Wang R (2017) Ensemble learning and SMOTE based fault diagnosis system in self-organizing cellular networks, GLOBECOM 2017–2017. IEEE Global communications conference, Singapore, pp 1–6

    Google Scholar 

  5. 5.

    Wang Y, Zhu K, Sun M, Deng Y (2019) An ensemble learning approach for fault diagnosis in self-organizing heterogeneous networks. IEEE Access 7:125662–125675

    Article  Google Scholar 

  6. 6.

    Iyer AP, Li LE, Stoica I (2017) Automating diagnosis of cellular radio access network problems. In: Proceedings of the 23rd annual international conference on mobile computing and networking. ACM, New York, pp 79–87

  7. 7.

    Mfula H, Nurminen JK (2017) Adaptive root cause analysis for self-healing in 5G networks. 2017 International conference on high performance computing & simulation (HPCS), Genoa, pp 136–143

    Google Scholar 

  8. 8.

    He HB, Garcia EA (2009) Learning from imbalanced data. IEEE Trans Knowl Data Eng 21(9):1263–1284

    Article  Google Scholar 

  9. 9.

    Settles B (2009) Active learning literature survey. Computer Sciences Technical Report 1648 University of Wisconsin–Madison

  10. 10.

    Tianqi C, Guestrin C (2016) Xgboost: a scalable tree boosting system. In: Proceedings of the 22nd ACM sigkdd international conference on knowledge discovery and data mining. ACM, New York, pp 785–794

  11. 11.

    Chawla NV, Bowyer KW, Hall LO, Kegelmeyer W P (2002) Smote: synthetic minority over-sampling technique. J Artif Intell Res 16(1):321–357

    Article  Google Scholar 

  12. 12.

    Han H, Wang WY, Mao BH (2005) Borderline-SMOTE: a new over-sampling method in imbalanced data sets learning. In: Proceedings of the international conference intelligent computing, pp 878–887

  13. 13.

    Zhang T, Zhu K, Niyato D (2019) A generative adversarial learning based approach for cell outage detection in self-organizing cellular networks, vol 9, pp 171–174

  14. 14.

    Muñoz P et al (2011) Computationally efficient design of a dynamic systemlevel LTE simulator. Int J Electron Telecommun 57(3):347–358

    Article  Google Scholar 

  15. 15.

    Virdis A, Stea G, Nardini G, Obaidat M S, Ören T, Kacprzyk J, Filipe J (2016) Simulating lte/lte-advanced networks with simulte. In: Simulation and modeling methodologies technologies and applications. Springer International Publishing, Cham, pp 83–105

  16. 16.

    Rupp M, Schwarz S, Taranetz M (2016) The Vienna LTE-advanced simulators: up and downlink, link and system level simulation, 1st edn. Springer Publishing Company Incorporated

  17. 17.

    NS3[O], https://www.nsnam.org/

  18. 18.

    Baldo N, Miozzo M, Requena-Esteso M, Nin-Guerrero J (2011) An open source product-oriented lte network simulator based on ns-3. In: Proceedings of the 14th ACM international conference on modeling analysis and simulation of wireless and mobile systems (MSWIM), pp 293–298

  19. 19.

    Baldo N, Requena-Esteso M, Miozzo M, Kwan R (2013) An open source model for the simulation of LTE handover scenarios and algorithms in ns-3. In: Proceedings of the 16th ACM international conference on modeling, analysis & simulation of wireless and mobile systems, ser. MSWiM ’13. ACM, New York, pp 289–298

  20. 20.

    Forkel I, Kemper A, Pabst R, Hermans R (2002) The effect of electrical and mechanical antenna down-tilting in UMTS networks. Third international conference on 3G mobile communication technologies, London, pp 86–90

    Google Scholar 

  21. 21.

    3GPP, Evolved universal terrestrial radio access (E-UTRA); Further advancements for E-UTRA Physical layer aspects, ser. TR. 3GPP, 2015, no. TR36.814, Rel-9 v1.3.0. [Online]. Available: http://www.3gpp.org/ftp/Specs/html-info/36814.htm

  22. 22.

    Andrei M, Macaluso I, DaSilva L A (2017) System level evaluation and validation of the ns-3 LTE module in 3GPP reference scenarios Q2SWinet@MSWiM

  23. 23.

    Gómez-Andrades A, Múnoz P, Serrano I, Barco R (2016) Automatic root cause analysis for LTE networks based on unsupervised techniques. IEEE Trans Veh Technol 65(4):2369–2386

    Article  Google Scholar 

  24. 24.

    Tang YP, Li GX, Huang SJ (2019) ALiPy: active learning in python. arXiv:1901.03802

Download references

Acknowledgments

This work is supported by Fundamental Research Funds for the Central Universities (NE2018107).

Author information

Affiliations

Authors

Corresponding author

Correspondence to Kun Zhu.

Additional information

Publisher’s Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Chen, M., Zhu, K. & Chen, B. Root Cause Analysis for Self-organizing Cellular Network: an Active Learning Approach. Mobile Netw Appl (2020). https://doi.org/10.1007/s11036-020-01589-1

Download citation

Keywords

  • Active learning
  • Self-healing
  • Fault diagnosis
  • XGBoost