Systems and Means of Informatics
2021, Volume 31, Issue 3, pp 135-143
AN EXAMPLE OF NEURAL NETWORK USAGE FOR ASSIGNING A MODULATION-CODE SCHEME TO A 5G BASE STATION SCHEDULER
- E. V. Bobrikova
- A. A. Platonova
- Yu. V. Gaidamaka
- S. Ya. Shorgin
Abstract
The article proposes a method for assigning a modulation-code scheme by a base station scheduler based on predicting the value of the signal-to- interference ratio on the mobile user's equipment at the next time slot from a sequence of known values of this ratio in the past. For prediction, a model of a single-layer neural network is built in the work, by the example of which a machine learning process is shown for solving a multiparametric optimization problem using the stochastic gradient method. The trained neural network for the predicted value of the signal/interference ratio allows the scheduler to correctly select the modulation-code scheme for the user, thereby ensuring the level of quality of data transmission in the radio channel required for the provision of the service.
[+] References (6)
- Ghosh, A., and R. Ratasuk. 2011. Essentials of LTE and LTE-A. Cambridge, U.K.: Cambridge University Press. 264 p. doi: 10.1017/CB09780511997082.
- Matematicheskie metody obucheniya po pretsedentam (teoriya obucheniya mashin) [Mathematical teaching methods by precedents (machine learning theory)]. Available at: http://www.machinelearning.ru/wiki/images/6/6d/Voron-ML-1.pdf (accessed September 3, 2021).
- Averkin, A. N., M. G. Gaaze-Rapoport, and D. A. Pospelov. 1992. Tolkovyy slovar' po iskusstvennomu intellektu [Dictionary of artificial intelligence]. Moscow: Radio i svyaz'. 256 p.
- Trask, A.W. 2019. Grokking deep learning. New York, NY: Manning Publications. 336 p.
- Gaidamaka, Yu. V., K. E. Samouylov, and S. Ya. Shorgin. 2017. Metod modelirovaniya kharakteristik interferentsii pri pryamom vzaimodeystvii peremeshchayushchikhsya ustroystv v geterogennoy besprovodnoy seti pyatogo pokoleniya [A method for modeling interference characteristics during direct interaction of roaming devices in a heterogeneous fifth generation wireless network]. Informatika i ee Primeneniya - Inform. Appl. 11(4): 2-9.
- Bobrikova, E., A. Platonova, I. Yartseva, and E. Khairov. 2021. K zadache predskazaniya SINR v besprovodnoy seti s podvizhnymi pol'zovatelyami s pomoshch'yu apparata neyronnykh setey [To the problem of predicting SINR ina wireless network with mobile users with a neural network apparatus]. Informatsionno-telekommunikatsionnye tekhnologii i matematicheskoe modelirovanie vysokotekhnologichnykh sistem [Information and telecommunication technologies and mathematical modeling of high-tech systems]. RUDN University Publs. Moscow. 30-32.
[+] About this article
Title
AN EXAMPLE OF NEURAL NETWORK USAGE FOR ASSIGNING A MODULATION-CODE SCHEME TO A 5G BASE STATION SCHEDULER
Journal
Systems and Means of Informatics
Volume 31, Issue 3, pp 135-143
Cover Date
2021-11-10
DOI
10.14357/08696527210312
Print ISSN
0869-6527
Publisher
Institute of Informatics Problems, Russian Academy of Sciences
Additional Links
Key words
SINR; machine learning; neural network
Authors
E. V. Bobrikova , A. A. Platonova , Yu. V. Gaidamaka , , and S. Ya. Shorgin
Author Affiliations
Peoples' Friendship University of Russia (RUDN University), 6 Miklukho- Maklaya Str., Moscow 117198, Russian Federation
Federal Research Center "Computer Science and Control", Russian Academy of Sciences, 44-2 Vavilov Str., Moscow 119333, Russian Federation
|