Research of mobile broadband communication using artificial intelligence

DOI: 10.31673/2412-9070.2023.020309

Abstract

The current conditions force us to think about what will be the sixth generation (6G) mobile communications with the introduction and deployment of fifth generation (5G) technologies. The path of development of 6G and the further development of technologies will be considered in this article. First, let's get acquainted with modern 5G technologies and point out the need to study 6G. Considering the current and new development of wireless communication, we expect 6G to include three main aspects, namely mobile ultra-wide communication, super internet of things (IoT) and artificial intelligence (AI). Terahertz (THz) communications can be used to support mobile ultra-broadband, symbiotic radio and satellite communications can be used to achieve the super-internet of things, and machine learning methods are promising candidates for AI. The idea of a deep learning algorithm is considered, which is to resemble the process of perception in the brain using a deep neural network. Generally, a deep neural network consists of three layers i.e. input layer, hidden layer and source layer. In particular, the input layer provides input ports for information about the state of the environment observed by the learning agent, the hidden layer extracts the characteristics of the input information, and the output layer makes decisions regarding classifications or regressions. The minimum element of a deep neural network is a neuron responsible for processing and transmitting information between different neurons/layers. For each technology, we provide the basic principle, key tasks, as well as the most modern approaches and solutions.

Keywords: communication; artificial intelligence; mobile ultra-wide communication; sixth generation mobile communication; symbiotic radio; satellite communication; artificial intelligence; machine learning.

References
1. Підвищення показників якості системи управління послугами мережами майбутнього / В. Б. Толубко, Л. Н. Беркман, Л. П. Крючкова, А. Ю. Ткачов // Наукові записки Укр. наук.-дослід. ін-ту зв'язку. 2018. № 3. С. 5–11.
2. Ambient Backscatter Communications: A Contemporary Survey / N. V. Huynh, D. T. Hoang, X. Lu [et al.] // IEEE Commun. Surveys Tuts. 2018. vol. 20, no. 4. 4th Quart. P. 2889–2922.
3. Mao Q., Hu F., Hao Q. Deep learning for intelligent wireless networks: a comprehensive survey // IEEE Commun. Survey Tuts. 2018. vol. 20, no. 4. 4th Quart. P. 2595–2621.
4. Vougioukas G., Bletsas A. Switching frequency techniques for universal ambient backscatter networking // IEEE J. Select. Areas Commun. Feb. 2019. vol. 37, no. 2. P. 464–477.
5. Modulation in the air: Backscatter communication over ambient OFDM carrier / G. Yang, Y.-C. Liang, R. Zhang, Y. Pei // IEEE Trans. Commun. Mar. 2018. vol. 66, no. 3. P. 1219–1233.
6. Yang G., Zhang Q., Liang Y.-C. Cooperative ambient backscatter communication systems for internet-of-things // IEEE Internet of Things. Apr. 2018. vol. 5, no. 2. P. 1116–1130.
7. 3GPP TR 22.822. Study on Using Satellite Access in 5G; Stage 1 (Release 16). June 2018.
8. Zhang C., Patras P., Haddadi H. Deep learning in mobile and wireless networking: a survey. Availavble in arXiv:1803.04311 [cs.NI].
9. Application of machine learning in wireless networks: key techniques and open issues / Y. Sun, M. Peng, Y. Zhou [et al.] // Available in: arXiv: 1811.06776 [cs.NI].
10. Intelligent wireless communications enabled by cognitive radio and machine learning / X. Zhou, M. Sun, G. Y. Li, B.-H. F. Juang // China Commun. Dec. 2018. vol. 15, no. 12. P. 16–48.