Uplink Throughput Prediction in Cellular Mobile Networks

Authors: Engin Eyceyurt, Josko Zec

Abstract:

The current and future cellular mobile communication networks generate enormous amounts of data. Networks have become extremely complex with extensive space of parameters, features and counters. These networks are unmanageable with legacy methods and an enhanced design and optimization approach is necessary that is increasingly reliant on machine learning. This paper proposes that machine learning as a viable approach for uplink throughput prediction. LTE radio metric, such as Reference Signal Received Power (RSRP), Reference Signal Received Quality (RSRQ), and Signal to Noise Ratio (SNR) are used to train models to estimate expected uplink throughput. The prediction accuracy with high determination coefficient of 91.2% is obtained from measurements collected with a simple smartphone application.

Keywords: Drive test, LTE, machine learning, uplink throughput prediction.

References:

[1] J. Thomas Barnett, "Cisco Visual Networking Index (VNI) Global and Americas/EMEAR Mobile Data Traffic Forecast, 2017–2022," Cisco, 2019.
[2] Y. Egi, E. Eyceyurt, I. Kostanic, C. E. Otero, "An Efficient Approach for Evaluating Performance in LTE Wireless Networks," Las Vegas, 2017.
[3] Union, International telecommunication, "IMT traffic estimates for the years 2020 to 2030," Geneva, 2015.
[4] P. &. i. Inc, "Global Mobile Data Traffic Forecast, 2012 – 2017," Austin TX, 2013.
[5] Ericsson Mobility Report, Managing User Experience, Ericsson, 2016.
[6] Otero, Y. Egi C., "Machine-Learning and 3D Point-Cloud Based Signal Power Path Loss Model for the Deployment of Wireless Communication Systems," IEEE Access, vol. 7, pp. 42507-42517, 2019.
[7] Y. Egi, C. Otero, M. Ridley and E. Eyceyurt, "An Efficient Architecture for Modeling Path Loss on Forest Canopy Using LiDAR and Wireless Sensor Networks Fusion," in 23rd European Wireless Conference, Dresden, Germany, 2017.
[8] H. Konoshi, K. Kanai, J Katto, "Improvement of Throughput prediction Accuracy for Video Streaming in Mobile Environment," in IEEE 3rd Global Conference on Consumer Electronics, Tokyo, 2014.
[9] C. Yue, R. Jin, K. Suh, Y. Qin, B. Wang and W. Wei;, "LinkForecast: Cellular Link Bandwidth Prediction in LTE Networks," IEEE Transactions on Mobile Computing, vol. 17, pp. 1582-1594, 2018.
[10] Y. Liu and J.Y.B. Lee, "An Empirical Study of Throughput Prediction in Mobile Data Networks," in IEEE Global Communications Conference, San Diego, 2015.
[11] D. Lee, D. Lee, M. Choi and J. Lee, "Prediction of Network Throughput using ARIMA," in International Conference on Artificial Intelligence in Information and Communication (ICAIIC), Fukuoka, Japan, 2020.
[12] B. Wei, M. Okano, K. Kanai, W. Kawakami and J. Katto, "Throughput Prediction Using Recurrent Neural Network Model," in IEEE 7th Global Conference on Consumer Electronics, Nara, 2018.
[13] I. Oussakel, P. Owezarski, P. Berthou, "Cellular Uplink Bandwidth Prediction Based on Radio Measurements," in MobiWac, Miami, 2019.
[14] E. T. 1. 2. V. (2018-07), "Technical Specification Physical layer measurements, 5G; NR," 2018.
[15] D. S. Mehta and S. Chen, "A spearman correlation based star pattern recognition," in IEEE International Conference on Image Processing (ICIP), Beijing, 2017.