A Metric for Determining the Significance of Failures and Its Use in Anomaly Detection

Case Study: Mobile Network Management Data from LTE Network
  • Robin Babujee JeromeEmail author
  • Kimmo Hätönen
Conference paper
Part of the Communications in Computer and Information Science book series (CCIS, volume 517)


In big data analytics and machine learning applications on telecom network measurement data, accuracy of findings during the analysis phase greatly depends on the quality of the training data set. If the training data set contains data from Network Elements (NEs) with high number of failures and high failure rates, such behavior will be assumed as normal. As a result, the analysis phase will fail to detect NEs with such behavior. High failure ratios have traditionally been considered as signs of faults in NEs. Operators use well-known Key Performance Indicators (KPIs), such as, e.g., Drop Call Ratio and Handover failure ratio to identify misbehaving NEs. The main problem with these KPIs based on failure ratios is their unstable nature. This paper proposes a method of measuring the significance of failures and its use in training set filtering.


Anomaly detection Pre-processing Self-Organizing maps Training set filtering 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Kumpulainen, P.: Anomaly Detection for Communication Network Monitoring Applications, Doctoral Thesis in Science & Technology, Tampere: Tampere University of Technology (2014)Google Scholar
  2. 2.
    Kumpulainen, P., Hätönen, K.: Anomaly detection algorithm test bench for mobile network management. In: The MathWorks Conference Proceedings of the MathWorks/MATLAB User Conference Nordic (2008)Google Scholar
  3. 3.
    Chernogorov, F.: Detection of Sleeping Cells in Long Term Evolution Mobile Networks, Master’s Thesis in Mobile Technology, University of Jyväskylä, JyväskyläGoogle Scholar
  4. 4.
    Kumpulainen, P., Kylväjä, M., Hätönen, K.: Importance of scaling in unsupervised distance-based anomaly detection (2009)Google Scholar
  5. 5.
    Kohonen, T.: Self-Organizing Maps. Springer, Berlin (1997)CrossRefzbMATHGoogle Scholar
  6. 6.
    Laiho, J., Raivio, K., Lehtimäki, P., Hätönen, K., Simula, O.: Advanced Analysis Methods for 3G Cellular Network. IEEE Transactions on Wireless Communications 4(3), 930–942 (2005)CrossRefGoogle Scholar
  7. 7.
    Kumpulainen, P., Hätönen, K.: Local anomaly detection for mobile network monitoring. Information Sciences 178(20), 3840–3859 (2008)CrossRefGoogle Scholar
  8. 8.
    Yin, H.: The Self-Organizing Maps: Background, Theories, Extensions and Applications. Computational Intelligence: A Compendium: Studies in Computational Intelligence 115, 715–762 (2008)CrossRefGoogle Scholar
  9. 9.
    Suutarinen, J.: Performance Measurements of GSM Base Station System. Thesis (Lic.Tech.), Tampere University of Technology, Tampere (1994)Google Scholar
  10. 10.
    Höglund, A.J., Hätönen, K., Sorvari, A.S.: A computer host-based user anomaly detection system using the self-organizing map. IEEE-INNS-ENNS International Joint Conference on Neural Networks (IJCNN) 5, 411–416 (2000)CrossRefGoogle Scholar
  11. 11.
    Kylväjä, M., Hätönen, K., Kumpulainen, P., Laiho, J., Lehtimäki, P., Raivio, K., Vehviläinen, P.: Trial Report on Self-Organizing Map Based Analysis Tool for Radio Networks. Vehicular Technology Conference 4, 2365–2369 (2004)Google Scholar
  12. 12.
    Anonymous, Serve atOnce Traffica. Nokia Solutions and Networks Oy. (accessed December 16, 2014)
  13. 13.
    Hätönen, K.: Data mining for telecommunications network log analysis. Doctoral Thesis, Helsinki University, Helsinki (2009)Google Scholar

Copyright information

© Springer International Publishing Switzerland 2015

Authors and Affiliations

  1. 1.Department of Communication EngineeringAalto University School of Electrical EngineeringEspooFinland
  2. 2.Nokia Networks ResearchEspooFinland

Personalised recommendations