Review of spectrum sensing models LTE and NR signals

Cover Page

Cite item

Full Text

Open Access Open Access
Restricted Access Access granted
Restricted Access Subscription or Fee Access

Abstract

The paper is devoted to the review of models of artificial intelligence use for determining by the receiver of cognitive radio information about the target signal structure on the basis of neural network approach. It describes how the models capture and partition LTE and 5G NR signals in spectrum sensing. Deep learning neural network semantic segmentation neural network models are used to identify LTE and NR signals. The considered set of models can be used for practical implementation of spectrum sensing in dynamic spectrum access in promising cognitive radio networks.

Full Text

Restricted Access

About the authors

G. A. Fokin

СПбГУТ им. проф. М.А. Бонч-Бруевича

Author for correspondence.
Email: grihafokin@gmail.com

д.т.н., проф.

Russian Federation

References

  1. Тихвинский В.О., Девяткин Е.Е., Смирнов Ю.Я., Ахмедиаров В.А. Использование технологий ИИ для обеспечения информационной безопасности в сетях 5G // ПЕРВАЯ МИЛЯ. 2024. № 4 (120). С. 44−50.
  2. Тихвинский В.О., Девяткин Е.Е., Савочкин А.А., Смирнов Ю.Я., Новикова Т.В. Использование технологий искусственного интеллекта для анализа сетевых данных в базовой сети 5G // ПЕРВАЯ МИЛЯ. 2023. № 5 (113). С. 46−55.
  3. Тихвинский В.О., Терентьев С.В., Девяткин Е.Е. Применение технологий искусственного интеллекта в сетях 5G // ПЕРВАЯ МИЛЯ. 2023. № 3 (111). С. 52−61.
  4. Тихвинский В., Девяткин Е., Белявский В. По пути от 5G к 5G Advanced: Релизы 17 и 18 // ПЕРВАЯ МИЛЯ. 2021. № 6 (98). С. 38−47.
  5. Olfati M., Parmar K. Deep Learning and AI for 5G Technology: Paradigms // Artificial Intelligence Applications and Innovations (AIAI) 2021. Springer International Publishing Proceedings, 2021. PP. 398−407.
  6. Almutairi M.S. Deep Learning-Based Solutions for 5G Network and 5G-Enabled Internet of Vehicles: Advances, Meta-Data Analysis and Future Direction // Mathematical Problems in Engineering. 2022. Vol. 1. P. 6855435.
  7. Aslam M.M., Du L., Zhang X., Chen Y., Ahmed Z., Qureshi B. Sixth generation (6G) cognitive radio network (CRN) application requirements security issues and key challenges // Wireless Communications and Mobile Computing. 2021. Vol. 1. P. 1331428.
  8. Zhang Y., Luo Z. A Review of Research on Spectrum Sensing Based on Deep Learning // Electronics. 2023. Vol. 12. Iss. 21. P. 4514.
  9. Ivanov A., Tonchev K., Poulkov V., Manolova A. Probabilistic Spectrum Sensing Based on Feature Detection for 6G Cognitive Radio: A Survey // IEEE Access. 2021. Vol. 9. PP. 116994–117026.
  10. Zappone A., Di Renzo M., Debbah M. Wireless Networks Design in the Era of Deep Learning: Model-Based, AI-Based, or Both? // IEEE Transactions on Communications. 2019. Vol. 67. Iss. 10. PP. 7331–7376.
  11. Morocho-Cayamcela M.E., Lee H., Lim W. Machine Learning for 5G/B5G Mobile and Wireless Communications: Potential, Limitations, and Future Directions // IEEE Access. 2019. Vol. 7. PP. 137184–137206.
  12. Syed S.N. et al. Deep Neural Networks for Spectrum Sensing: A Review // IEEE Access. 2023. Vol. 11. PP. 89591−89615.
  13. Tekbıyık K., Akbunar Ö., Ekti A.R., Görçin A., Kurt G.K., Qaraqe K.A. Spectrum Sensing and Signal Identification With Deep Learning Based on Spectral Correlation Function // IEEE Transactions on Vehicular Technology. 2021. Vol. 70. Iss. 10. PP. 10514−10527.
  14. Alhazmi M.H., Alymani M., Alhazmi H., Almarhabi A., Samarkandi A., Yao Y. 5G Signal Identification Using Deep Learning // 2020 29th Wireless and Optical Communications Conference (WOCC) (Newark, NJ, USA). IEEE, 2020. PP. 1−5.
  15. Ngo T., Kelley B., Rad P. Deep Learning Based Prediction of Signal-to-Noise Ratio (SNR) for LTE and 5G Systems // 2020 8th International Conference on Wireless Networks and Mobile Communications (WINCOM) (Reims, France). IEEE, 2020. PP. 1−6.
  16. Ahmed R., Chen Y., Hassan B. Deep learning-driven opportunistic spectrum access (OSA) framework for cognitive 5G and beyond 5G (B5G) networks // Ad Hoc Networks. 2021. Vol. 123. P. 102632.
  17. Wasilewska M., Bogucka H., Kliks A. Spectrum sensing and prediction for 5g radio // International Conference on Big Data Technologies and Applications. Cham: Springer International Publishing, 2020. PP. 176−194.
  18. Wasilewska M., Bogucka H., Kliks A. Federated learning for 5G radio spectrum sensing // Sensors. 2021. Vol. 22. Iss. 1. PP. 198.
  19. Capture and Label NR and LTE Signals for AI Training. MathWorks. [Электронный ресурс]. URL: https://www.mathworks.com/help/wireless-testbench/ug/capture-and-label-nr-and-lte-signals-for-ai-training.html (дата обращения 23.09.2024).
  20. Spectrum Sensing with Deep Learning to Identify 5G and LTE Signals. MathWorks. [Электронный ресурс]. URL: https://www.mathworks.com/help/comm/ug/spectrum-sensing-with-deep-learning-to-identify-5g-and-lte-signals.html (дата обращения 23.09.2024).
  21. Identify LTE and NR Signals from Captured Data Using SDR and Deep Learning. MathWorks. [Электронный ресурс]. URL: https://www.mathworks.com/help/wireless-testbench/ug/identify-lte-and-nr-signals-from-captured-data-using-sdr-and-deep-learning.html (дата обращения 23.09.2024).
  22. LTE Toolbox. MathWorks. [Электронный ресурс]. URL: https://www.mathworks.com/products/lte.html (дата обращения 23.09.2024).
  23. Toolbox. MathWorks. [Электронный ресурс]. URL: https://www.mathworks.com/products/5g.html (дата обращения 23.09.2024).
  24. Communications Toolbox. MathWorks. [Электронныйресурс]. URL: https://www.mathworks.com/products/communications.html (дата обращения 23.09.2024).
  25. Computer Vision Toolbox. MathWorks. [Электронныйресурс]. URL: https://www.mathworks.com/products/computer-vision.html (дата обращения 23.09.2024).
  26. Deep Learning Toolbox. MathWorks. [Электронныйресурс]. URL: https://www.mathworks.com/products/deep-learning.html (дата обращения 23.09.2024).
  27. Фокин Г.А., Буланов Д.В., Волгушев Д.Б. Модельно-ориентированное проектирование систем радиосвязи на основе ПКР // Вестник связи. 2015. № 6. С. 26−30.
  28. Фокин Г.А., Лаврухин В.А., Волгушев Д.А., Киреев А.В. Модельно-ориентированное проектирование на основе SDR // Системы управления и информационные технологии. 2015. № 2 (60). С. 94−99.
  29. Фокин Г.А., Волгушев Д.Б., Харин В.Н. Использование SDR технологии для задач сетевого позиционирования. Формирование опорных сигналов LTE // T-Comm: Телекоммуникации и транспорт. 2022. Т. 16. № 5. С. 28−47.
  30. lteFadingChannel. MathWorks. [Электронный ресурс]. URL: https://www.mathworks.com/help/lte/ref/ltefadingchannel.html (дата обращения 23.09.2024).
  31. nrCDLChannel. MathWorks. [Электронный ресурс]. URL: https://www.mathworks.com/help/5g/ref/nrcdlchannel-system-object.html (дата обращения 23.09.2024).
  32. Выбор слоя активации в нейронных сетях: как правильно выбрать для вашей задачи. [Электронный ресурс]. URL: https://habr.com/ru/articles/727506/ (дата обращения 23.09.2024).

Supplementary files

Supplementary Files
Action
1. JATS XML
Download
2. Fig. 1. Modeling of spectral probing procedures

Download (225KB)
Indexing metadata
3. Fig. 2. The order of capture and post-processing procedures during spectral probing

Download (271KB)
Indexing metadata
4. Fig. 3. Distribution of recognized signals

Download (155KB)
Indexing metadata
5. Fig. 4. Signal recognition matrix

Download (213KB)
Indexing metadata
6. Fig. 5. Image of the analyzed spectrogram

Download (461KB)
Indexing metadata

Copyright (c) 2024 Fokin G.A.