Analysis of the expansion of a GSM network using Gaussian Processes

  • Jhouben Janyk Cuesta Ramírez Ingeniero Electricista. Laboratorio de Investigación en Automática. Universidad Tecnológica de Pereira. Pereira
  • Álvaro Ángel Orozco Gutiérrez Ph.D. Bioingeniería, Docente Titular Universidad Tecnológica de Pereira. Pereira
  • Mauricio Alexánder Álvarez López Ph.D. Ciencias de la Computación, Docente Asociado Universidad Tecnológica de Pereira. Pereira
Keywords: Gaussian Processes, GSM networks, KPIs, machine learning, regression.


Abstract— the expansion plan of a Global System Mobile (GSM) network requires the analysis of some important variables known as key performance indicators (KPI) on the network. Network operators have tools for analyzing a KPI behavior on a particular network cell. This paper proposes a tool that illustrates graphically the behavior-in-time of a KPI in a whole geographical zone (including cell positions). A Gaussian process repressor is used over a real data set and time-space inference is performed. Finally we observe how a particular region presents high-KPI values most of the time. This alerts the network operator for including a solution in the formulation phase of the network expansion plan.


Download data is not yet available.


[1] C. Steven and P. Samuel, “On the Expansion of Cellular Wireless Networks”. Éole Polytechnique de Montréal, 2002.

[2] A.R. Mishra, Advanced Cellular Network Planning and Optimization: 2G/2.5G/3G… Evolution to 4G, John Wiley & Sons, 2006.

[3] J. Laiho, A. Wacker, and T. Novosad, Radio Network Planning and Optimization for UMTS, 2001 :Wiley

[4] C. Roberto, I. Tiziano and V. Luca. “Network monitoring and performance evaluation in a 3.5G network”. Computer Networks Vol. 51. 2007.

[5] Sukkhawatchani, P.; Usaha, W., “Performance evaluation of anomaly detection in cellular core networks using self-organizing map,” Electrical Engineering/Electronics, Computer, Telecommunications and Information Technology, 2008. ECTI-CON 2008. 5th International Conference, vol.1, no., pp.361, 364, 14-17 May 2008.

[6] A.K.M. Fazlul, Mohamed Mir, K. Abu. “Performance Analysis of UMTS cellular Network using Sectorization Based on Capacity and Coverage” IJACSA International Journal of Advanced Computer Science and Applications Vol. 1, No.6, 2011.

[7] Ye Ouyang and M. Hosein Fallah. “A performance Analysis for UMTS Packet Switched Network Based on Multivariate KPIs”. IJNGN International Journal of Next Generation Network, Vol.2, No.1, March 2010.

[8] Kumpulainen P, Särkioja M. et al. “Analysing 3G radio network performance with fuzzy methods”. Neurocomputing Vol. 107. 2013.

[9] C.E. Rasmussen and C. Williams, Gaussian Processes for Machine Learning. The MIT Press, 2006. 10 antes

[10] J.Q.Shi, R. Murray-Smith and D.M. Titterington, “Hierarchical Gaussian Process Mixtures for Regression”. Statics and Computing, Springer, 2005.

[11] A. Schwaighofer, M. Grigoras, V. Tresp and C. Hoffmann, “GPPS: A Gaussian Process Positioning System for Cellular Networks” in book: Advances in Neural Information Processing Systems 16. The MIT press, 2004.

[12] B. Ferris, D. Hähnel and D. Fox, “Gaussian Processes for Signal Strength-Based Location Estimation”. Proc. of Robotics: Science and Systems, 2006.

[13] Liutkus A. and Badeau R. and Richard G., “Multidimensional signal separation with Gaussian processes,” IEEE Statistical Signal Processing Workshop (SSP), 2011.

[14] F. Duvallet and A.D. Tews, “WiFi Position Estimation in Industrial Environments Using Gaussian Processes”, Intelligent Robots and Systems, 2008. IROS 2008. IEEE/RSJ International Conference on , vol., no., pp.2216,2221, 22-26 Sept. 2008

[15] C.M. Bishop, Pattern Recognition and Machine Learning. Springer, 2006.

[16] K. P. Murphy, Machine Learning a Probabilistic Perspective. The MIT Press, 2012, p. 1067.


[18] K. Chalupka, “Empirical evaluation of Gaussian Process approximation algorithms”, Master’s thesis, School of Informatics, University of Edinburgh, 2011
Research and Innovation Articles