Geodesic
Study of a celular operator servers load forecasting models efficiency
Matematičeskoe modelirovanie, Tome 35 (2023) no. 1, pp. 83-94.

Voir la notice de l'article provenant de la source Math-Net.Ru

The problem of predicting the possible loads in a cellular network operation can be reduced to building a forecast about the possible number of calls directed to one gateway (PGW) within a given period of time. Possessing such data for all gateways within the network, it is possible to organize the optimal distribution of resources, prevent overloading of the gateways and, as a result, failures in the entire network operation. A statistical analysis of actual data collected by automated measuring systems on the nodes of a mobile network was carried out, the data most suitable for building forecasting models were identified. The results of the research on the possibility and effectiveness of the application of the mathematical models realized in constructing such a forecast by using such machine learning methods as linear regression, KNN and random forest are presented. It has been established that in order to solve the problem of building a short-term forecast about the number of requests that are to enter the server, it is not necessary to use complex models that require computing resources. Based on the calculated quality metrics, it was found that the most accurate forecast can be obtained by using a linear regression model.
Keywords: linear regression, $k$-nearest neighbors, random forest, predictive models. 
@article{MM_2023_35_1_a5,
     author = {I. V. Semenova and R. E. Ildiyarov},
     title = {Study of a celular operator servers load forecasting models efficiency},
     journal = {Matemati\v{c}eskoe modelirovanie},
     pages = {83--94},
     publisher = {mathdoc},
     volume = {35},
     number = {1},
     year = {2023},
     language = {ru},
     url = {http://geodesic.mathdoc.fr/item/MM_2023_35_1_a5/}
}
TY  - JOUR
AU  - I. V. Semenova
AU  - R. E. Ildiyarov
TI  - Study of a celular operator servers load forecasting models efficiency
JO  - Matematičeskoe modelirovanie
PY  - 2023
SP  - 83
EP  - 94
VL  - 35
IS  - 1
PB  - mathdoc
UR  - http://geodesic.mathdoc.fr/item/MM_2023_35_1_a5/
LA  - ru
ID  - MM_2023_35_1_a5
ER  - 
%0 Journal Article
%A I. V. Semenova
%A R. E. Ildiyarov
%T Study of a celular operator servers load forecasting models efficiency
%J Matematičeskoe modelirovanie
%D 2023
%P 83-94
%V 35
%N 1
%I mathdoc
%U http://geodesic.mathdoc.fr/item/MM_2023_35_1_a5/
%G ru
%F MM_2023_35_1_a5
I. V. Semenova; R. E. Ildiyarov. Study of a celular operator servers load forecasting models efficiency. Matematičeskoe modelirovanie, Tome 35 (2023) no. 1, pp. 83-94. http://geodesic.mathdoc.fr/item/MM_2023_35_1_a5/

[1] V. M. Bezruk, I. V. Korsun, V. A. Tikhonov, N. V. Kudriavtseva, “Issledovanie vozmozhnoste prognozirovaniia trafika seti mobilno cviazi”, Vostochno-Evropeski zhurnal peredovykh tekhnologi, 2010, no. 4/9(46), 58–62

[2] Du Xunsheng, H. Zhang, H. V. Nguyen, “Stacked LSTM Deep Learning Model for Traffic Prediction in Vehicle-to-Vehicle Communication”, 2017 IEEE 86th Vehicular Technology Conference (VTC-Fall) (Toronto, ON, Canada, 2017), 1–5

[3] A. R. Abdellah, A. K. Mahmood, A. Paramonov, A. Koucheryavy, “IoT traffic prediction using multi-step ahead prediction with neural network”, 2019 11th International Congress on Ultra Modern Telecommunications and Control Systems and Workshops (ICUMT), 2019, 1–4

[4] L. Paradis, Q. Han, “A survey of fault management in wireless sensor networks”, Journal of Network and Systems Management, 15:2 (2007), 171–190 | DOI | MR

[5] M. E. M. Cayamcela, W. Lim, “Artificial intelligence in 5G technology: A survey”, Proc. Int. Conf. Inf. Commun. Technol. Converg., ICTC (Oct. 2018), v. 1, 860–865

[6] J.E.P. Box, G.M. Jenkins, Time series analysis, Holden-Day, San Francisco, 1970, 553 pp. | MR

[7] T. Hastie, R. Tibshirani, J. Friedman, The Elements of Statistical Learning: Data Mining, Inference, and Prediction, Springer, N.Y., 2009 | MR

[8] E. Z. Demidenko, Linenaia i nelinenaia regressiia, Finansy i statistika, M., 1981, 302 pp. | MR

[9] F. R. Scott, Accurately Measuring Model Prediction Error, , 2012 http://scott.fortmann-roe.com/docs/MeasuringError.html

[10] M. Mullin, R. Sukthankar, “Complete cross-validation for nearest neighbor classifiers”, Proc. of International Conference on Machine Learning (San Francisco, CA, 2000)

[11] L. Breiman, “Random Forests”, Machine Learning, 45:1 (2001), 5–32 | DOI | MR

[12] R. E. Ildiiarov, I. V. Semenova, “Primenenie mnozhestvenno regressii dlia prognozirovaniia peregruzki serverov mobilnykh operatorov”, XXV Tupolevskie chteniia (shkola molodykh uchenykh), Mezhdunarodnaia molodezhnaia nauchnaia konferentsiia, Sbornik dokladov (10-11 noiabria 2021), v. 5, Izd-vo IP Sagieva A.P., Kazan, 2021, 309–312