Извините, этот техт доступен только в “Американский Английский”. For the sake of viewer convenience, the content is shown below in the alternative language. You may click the link to switch the active language.
ANALYSIS OF UNSUCCESSFUL E-RAB PROTOCOL CONNECTIONS ON THE LTE-A STANDARD MOBILE COMMUNICATION NETWORK
DOI: 10.36724/2072-8735-2020-14-7-4-12
Vladimir A. Fadeev, Kazan National Research Technical University named after A.N. Tupolev-KAI, Kazan, Russia, VAFadeev@kai.ru
Shaykhrozy V. Zaydullin, Kazan National Research Technical University named after A.N. Tupolev-KAI, Kazan, Russia, shvzaydullin@stud.kai.ru
Alexander A. Bogdanov, Kazan National Research Technical University named after A.N. Tupolev-KAI, Kazan, Russia, afnadeev@kai.ru
Abstract
In this paper, we consider Key Performance Identifiers (KPI) of a mobile communication network of one of the regional cellular operators of the Russian Federation, namely, the percentage of unsuccessful E-RAB (EPS Radio Access Bearer) connections in the LTE-A standard segment. As part of the study, the dynamics of a parameter’s change in time is given, the statistical and correlation characteristics of the selected KPI are analyzed, and a list of possible causes of unsuccessful connections with fractions showing the predominance of one or another reason for the considered operator is given. In order to identify stable network operation states according to the selected criterion, the article provides a clustering analysis of available statistics using the K-means and EM-algorithm. The elbow criterion for the K-means method and the Bayesian Information Criterion (BIC) were used as selection criteria for the number of main clusters. As part of the increase of detailization for identified reasons of deviations from the normal operation of a mobile network of the values of unsuccessful connections via the E-RAB protocol, a scheme of a hardware-software complex for collecting and transmitting information for monitoring needs is proposed. All components of the proposed hardware-software complex are open-licensed and open-source solutions that will allow the implementation of the proposed system with minimal costs. The results obtained in the framework of the study may be of interest to other mobile operators as part of the analysis, planning and optimization of LTE-A standard network resources within the one region or time zone.
Keywords: Key Performance Identifiers (KPI), RAB (Radio Access Bearer) protocol, E-RAB (E-UTRAN Radio Access Bearer) protocol, LTE (Long-Term Evolution) network, LTE-Advanced network.
References
1. Sun, Songlin, Meixia Fu, and Lexi Xu, eds. (2019). “Signal and Information Processing, Networking and Computers,” Proceedings of the 5th International Conference on Signal and Information Processing, Networking and Computers (ICSINC). Vol. 550. Springer.
2. Kreher, Ralf, and Karsten Gaenger. (2010). LTE signaling: troubleshooting and optimization. John Wiley & Sons.
3. ETSI TS 136 413 V12.3.0 (2014-09).
4. Academia. (2014). LTE Access Fault Diagnosis. [online] Available at: https://www.academia.edu/30048074/Confidential_Information_of_Huawei._ No_Spreading_Without_Permission_LTE_Access_Fault_Diagnosis [Accessed 14 Feb. 2020].
5. J.D. Hunter (2007). «Matplotlib: A 2D Graphics Environment», Computing in Science & Engineering, vol. 9, no. 3, pp. 90-95.
6. Freedman, David; Diaconis, Persi (December 1981). «On the histogram as a density estimator: L2 theory» (PDF). Probability Theory and Related Fields. Heidelberg: Springer Berlin. 57 (4), pp. 453- 476. doi:10.1007/BF01025868. ISSN 0178-8051. Retrieved 2009-01- 06.
7. Faming Liang. (2007). “Use of SVD-based probit transformation in clustering gene expression profiles,” Computational Statistics & Data Analysis. Vol. 51, Issue 12, 15 August 2007, pp. 6355-6366.
8. Lloyd, Stuart P. (1957). «Least square quantization in PCM». Bell Telephone Laboratories Paper. Published in journal much later: Lloyd, Stuart P. (1982). «Least squares quantization in PCM» (PDF). IEEE Transactions on Information Theory. 28 (2), pp. 129-137.
9. Hdbscan.readthedocs.io. (2020). Benchmarking Performance and Scaling of Python Clustering Algorithms — hdbscan 0.8.1 documentation. [online] Available at: https://hdbscan.readthedocs.io/en/latest/performance_and_scalability.html [Accessed 14 Feb. 2020].
10. Travis E. (2007). Oliphant. Python for Scientific Computing, Computing in Science & Engineering, 9, 10-20, DOI:10.1109/MCSE.2007.58
11. Fabian Pedregosa, Gal Varoquaux, Alexandre Gramfort, Vincent Michel, Bertrand Thirion, Olivier Grisel, Mathieu Blondel, Peter Prettenhofer, Ron Weiss, Vincent Dubourg, Jake Vanderplas, Alexandre Passos, David Cournapeau, Matthieu Brucher, Matthieu Perrot, Edouard Duchesnay. Scikit-learn: Machine Learning in Python, Journal of Machine Learning Research, 12, 2825-2830 (2011).
12. Garey M. Johnson D. Witsenhausen H. (1982-03-01). «The complexity of the generalized Lloyd — Max problem (Corresp.)». IEEE Transactions on Information Theory. 28 (2), pp. 255-256.
13. Paul D. McNicholas. (2010). “Model-based classification using latent Gaussian mixture models,” Journal of Statistical Planning and Inference. Vol. 140, Issue 5, May 2010, pp. 1175-1181.
14. Miin-Shen Yang, Chien-Yo Lai, Chih-Ying Lin. (2012). “A robust EM clustering algorithm for Gaussian mixture models,” Pattern Recognition. Vol. 45, Issue 11, November 2012, pp. 3950-3961.
15. Grus J. (2015). Data science from scratch: first principles with python. O’Reilly Media, Inc., pp. 199-202.
16. Sqlite.org. (2020). SQLite Home Page. [online] Available at: https://www.sqlite.org/index.html [Accessed 14 Feb. 2020].
17. GitHub. (2020). ClickHouse/ClickHouse. [online] Available at: https://github.com/ClickHouse/ClickHouse [Accessed 14 Feb. 2020].