CNN-Enabled Multiple Power-Levels Identification in Cognitive Radio Networks

Zhenyu TAN, Qi LIU, Zan LI, Danyang WANG, Ning ZHANG, Hong Ning DAI

Research output: Book Chapters | Papers in Conference ProceedingsConference paper (refereed)Referred Conference Paperpeer-review

Abstract

Spectrum sensing with transmit power identification can greatly facilitate the application of the hybrid spectrum access strategy in cognitive radio (CR) networks. Conventional model-driven methods suffer from severe performance degradation in low signal-to-noise ratio (SNR) regime. In this paper, we propose a multiple transmit power levels identification network (TPIN) which consists of three components. In the data preprocessing components, the covariance matrix (COV) of the received data is first employed as the observation data. Then, the residual network (ResNet) based feature extractor components is used to construct the test statistic by extracting high-dimensional features of the observation data. Furthermore, the likelihood ratio test (LRT) criterion is leveraged to design the cost function for obtaining the maximum posterior probability in the classifier components. Different from the assumption in conventional method, the prior probability of each transmit power levels is unknown to the TPIN, and the array of training set is randomly disturbed. In addition, in order to verify the ability of TPIN in data features extraction, a comparison reference experiment using a general test statistic (e.g., higher-order cumulative) as the observation data is introduced. Finally, simulation results demonstrate the identification performance of the COV-based (COV-TPIN) scheme.

Original languageEnglish
Title of host publication2022 IEEE Global Communications Conference, GLOBECOM 2022 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1881-1886
Number of pages6
ISBN (Electronic)9781665435406
ISBN (Print)9781665435406
DOIs
Publication statusE-pub ahead of print - 11 Jan 2023
Event2022 IEEE Global Communications Conference, GLOBECOM 2022 - Virtual, Online, Brazil
Duration: 4 Dec 20228 Dec 2022

Publication series

Name2022 IEEE Global Communications Conference, GLOBECOM 2022 - Proceedings

Conference

Conference2022 IEEE Global Communications Conference, GLOBECOM 2022
Country/TerritoryBrazil
CityVirtual, Online
Period4/12/228/12/22

Bibliographical note

Publisher Copyright:
© 2022 IEEE.

Keywords

  • cognitive radio
  • convolutional neural network
  • multiple transmit power levels identification
  • non-gaussian signal

Fingerprint

Dive into the research topics of 'CNN-Enabled Multiple Power-Levels Identification in Cognitive Radio Networks'. Together they form a unique fingerprint.

Cite this