Users’ Evaluation of Traffic Congestion in LTE Networks using Machine Learning Techniques

Authors

  • Bamidele Moses Kuboye

    Department of Information Technology, Federal University of Technology, P.M.B. 704, Akure, Nigeria
  • Adedamola Israel Adedipe

    Department of Information Technology, Federal University of Technology, P.M.B. 704, Akure, Nigeria
  • Segun Victor Oloja

    Department of Mathematics and Computer Sciences, University Medical Sciences, P.M.B. 536, Ondo, Nigeria
  • Olanrewaju Ayodeji Obolo

    Department of Mathematics and Computer Sciences, University Medical Sciences, P.M.B. 536, Ondo, Nigeria

DOI:

https://doi.org/10.30564/aia.v5i1.5452
Received: 8 February 2023 | Revised: 20 March 2023 | Accepted: 22 March 2023 | Published Online: 31 March 2023

Abstract

Over time, higher demand for data speed and quality of service by an increasing number of mobile network subscribers has been the major challenge in the telecommunication industry. This challenge is the result of an increasing population of human race and the continuous advancement in mobile communication industry, which has led to network traffic congestion. In an effort to solve this problem, the telecommunication companies released the Fourth Generation Long Term Evolution (4G LTE) network and afterwards the Fifth Generation Long Term Evolution (5G LTE) network that laid claims to have addressed the problem. However, machine learning techniques, which are very effective in prediction, have proven to be capable of great importance in the extraction and processing of information from the subscriber’s perceptions about the network. The objective of this work is to use machine learning models to predict the existence of traffic congestion in LTE networks as users perceived it. The dataset used for this study was gathered from some students over a period of two months using Google form and thereafter, analysed using the Anaconda machine learning platform. This work compares the results obtained from the four machine learning techniques employed that are k-Nearest Neighbour, Support Vector Machine, Decision Tree and Logistic Regression. The performance evaluation of the ML techniques was done using standard metrics to ascertain the real existence of congestion. The result shows that k-Nearest Neighbour outperforms all other techniques in predicting the existence of traffic congestion. This study therefore has shown that the majority of LTE network users experience traffic congestion.

Keywords:

Traffic Congestion; Fourth Generation (4G); Long Term Evolution (LTE); Machine Learning Techniques; KNN; SVM; Decision Tree; Logistic Regression; Subscribers

References

[1] Kuboye, B.M., 2019. Long term evolution (LTE) network evaluation in the south-west region of Nigeria. European Journal of Engineering and Technology Research. 4(3), 86-92.

[2] Tchao, E.T., Gadze, J.D., Agyapong, J.O., 2018. Performance evaluation of a deployed 4G LTE network. (IJACSA) International Journal of Advanced Computer Science and Applications. 9(3).

[3] Kuboye, B.M., 2017. Evaluation of broadband network performance in Nigeria. International Journal of Communications, Network and Sys-tem Sciences. 10(9), 199-207.

[4] Kim, J.H., 2021. Data-driven approach using machine learning for real-time flight path opti-mization [PhD thesis]. Atlanta: Georgia Institute of Technology.

[5] Amzat, J., Aminu, K., Kolo, V.I., et al., 2020. Coronavirus outbreak in Nigeria: Burden and socio-medical response during the first 100 days. International Journal of Infectious Diseases. 98, 218-224.

[6] Dan-Nwafor, C., Ochu, C.L., Elimian, K., et al., 2020. Nigeria’s public health response to the COVID-19 pandemic: January to May 2020. Journal of Global Health. 10(2), 1-9.

[7] Kuboye, B.M., Aratunde, T.O., Gbadamosi, A.A., 2021. Users’ evaluation of traffic con-gestion in LTE networks using deep learning techniques. International Journal of Computer Applications. 975, 8887.

[8] Idris, A., 2020. MTN Nigeria Records a Spike in Data Traffic, But Voice Revenue is Still King [In-ternet]. TechCabal [cited 2022 Sep 13]. Available from: https://techcabal.com/2020/04/30/mtn-q1-2020-financial-report-voice-data-revenue/

[9] Morocho-Cayamcela, M.E., Lee, H., Lim, W., 2019. Machine learning for 5G/B5G mobile and wireless communications: Potential, limitations, and future directions. IEEE Access. 7, 137184-137206.

[10] Samek, W., Stanczak, S., Wiegand, T., 2017. The convergence of machine learning and com-munications. arXiv:1708.08299. DOI: https://doi.org/10.48550/arXiv.1708.08299

[11] Stepanov, N., Alekseeva, D., Ometov, A. (edi-tors), et al., 2020. Applying machine learning to LTE traffic prediction: Comparison of bagging, random forest, and SVM. 2020 12th Interna-tional Congress on Ultra-Modern Telecommu-nications and Control Systems and Workshops (ICUMT); 2020 Oct 05-07; Brno, Czech Repub-lic. USA: IEEE. p. 119-123.

[12] Alekseeva, D., Stepanov, N., Veprev, A., et al., 2021. Comparison of machine learning tech-niques applied to traffic prediction of real wire-less network. IEEE Access. 9, 159495-159514.

[13] Khatouni, A.S., Soro, F., Giordano, D. (editors), 2019. A machine learning application for laten-cy prediction in operational 4g networks. 2019 IFIP/IEEE Symposium on Integrated Network and Service Management (IM); 2019 Apr 8-12; Arlington, VA, USA. USA: IEEE. p. 71-74.

[14] Fiandrino, C., Zhang, C., Patras, P., et al., 2020. A machine-learning-based framework for opti-mizing the operation of future networks. IEEE Communications Magazine. 58(6), 20-25.

[15] Hassan, H., Ahmed, I., Ahmad, R., et al., 2019. A machine learning approach to achieving ener-gy efficiency in relay-assisted LTE-A downlink system. Sensors. 19(16), 3461.

[16] Li, R., Zhao, Z., Zheng, J., et al., 2017. The learning and prediction of application-level traf-fic data in cellular networks. IEEE Transactions on Wireless Communications. 16(6), 3899-3912.

[17] Zaidi, S.A.R., 2021. Nearest neighbour methods and their applications in the design of 5G and beyond wireless networks. ICT Express. 7(4), 414-420.

[18] Khan, M.F., Yau, K.L.A., Noor, R.M., et al., 2020. Survey and taxonomy of clustering algo-rithms in 5G. Journal of Network and Computer Applications. 154, 102539.

[19] Statista Research Department, 2022. Number of Undergraduate Students at Universities in Nigeria as of 2019, by Gender and Discipline [Internet]. Statista [cited 2022 Jun 20]. Available from: https://www.statista.com/statistics/1262928/number-of-undergraduate-students-at-universi-ties-in-nigeria-by-gender-and-discipline/

[20] Idoko, C., 2021. 2.1 Million Students Studying in Nigerian Universities [Internet]. Nigerian Tri-bune [cited 2022 Jun 20]. Available from: https://tribuneonlineng.com/2-1-million-students-study-ing-in-nigerian-universities%E2%80%95-nuc/

[21] Yadav, S.K., Singh, S., Gupta, R., 2019. Bio-medical statistics, a beginner’s guide. Springer: Singapore. pp. 71-83.

[22] Patel, A., 2018. Machine Learning Algo-rithm Overview [Internet] [cited 2020 May 9]. Available from: https://medium.com/ml-research-lab/machine-learning-algorithm-over-view-5816a2e6303

[23] Kuhn, M., Johnson, K., 2013. Applied predictive modeling. Springer: New York. pp. 13.

[24] Polena, M., 2017. Performance analysis of cred-it scoring models on lending club data [Master’s thesis]. Prague: Charles University.

[25] Sun, Y., Peng, M., Zhou, Y., et al., 2019. Appli-cation of machine learning in wireless networks: Key techniques and open issues. IEEE Commu-nications Surveys and Tutorials. 21(4), 3072-3108.

[26] Mohamed, A.E., 2017. Comparative study of four supervised machine learning techniques for classification. International Journal of Applied. 7(2).

[27] Guerra, T., 2018. Machine Learning Based Han-dover Management for LTE Networks with Cov-erage Holes [Internet]. Available from:https://repositorio.ufrn.br/bitstream/123456789/26678/1/Machinelearningbased_Guerra_2018.pdf

[28] Karatzoglou, A., Meyer, D., Hornik, K., 2006. Support vector machines in R. Journal of Statis-tical Software. 15, 1-28.

[29] Awad, M., Khanna, R., 2015. Efficient learning machines: Theories, concepts, and applications for engineers and system designers. Springer Nature: Berlin. pp. 268.

[30] Grandini, M., Bagli, E., Visani, G., 2020. Met-rics for multi-class classification: An overview. arXiv:2008.05756. DOI: https://doi.org/10.48550/arXiv.2008.05756

[31] Marabad, S., 2021. Credit card fraud detection using machine learning. Asian Journal for Con-vergence in Technology. 7(2), 121-127.

Downloads

How to Cite

Kuboye, B. M., Adedipe, A. I., Oloja, S. V., & Obolo, O. A. (2023). Users’ Evaluation of Traffic Congestion in LTE Networks using Machine Learning Techniques. Artificial Intelligence Advances, 5(1), 8–24. https://doi.org/10.30564/aia.v5i1.5452

Issue

Vol. 5 , Iss. 1 (April 2023):

Article Type

Article

License

Copyright © 2023 Bamidele Moses Kuboye, Adedamola Israel Adedipe, Segun Victor Oloja, Olanrewaju Ayodeji Obolo

Creative Commons License

This is an open access article under the Creative Commons Attribution-NonCommercial 4.0 International (CC BY-NC 4.0) License.

Crossref
Scopus
Google Scholar
Europe PMC