We consider spectrum sensing problems in the orthogonal frequency division multiplexing access (OFDMA) cognitive radio sce-nario, where a secondary user with multiple antennas detects several consecutive subcarriers of an entire OFDM symbol occupied by multiple primary users. Specifically, an OFDM multicarrier covariance matrix convolutional neural network (CNN)-based approach is proposed for simul-taneously detecting the occupancy of all OFDM subcarriers, where the multicarrier sample covariance matrix array is specially set as the input of the CNN. The proposed approach can efficiently learn the energy information and correlation information between antennas and between subcar-riers to significantly improve the spectrum sensing performance. Numerical results demonstrate that the proposed method has a substantial per-formance advantage over the state-of-the-art spectrum sensing methods in an OFDMA scenario under the 5G new radio network.

National Key Laboratory of Science and Technology on Communica?tions, University of Electronic Science and Technology of China, Chengdu 611731, China;ZTE Corporation, Shenzhen 518057, China;State Key Laboratory of Mobile Network and Mobile Multimedia Technology, Shenzhen 518055, China

[1]ZHANG Jintao;HE Zhenqing;RUI Hua;XU Xiaojing-.Spectrum Sensing for OFDMA Using Multicarrier Covariance Matrix Aware CNN)[J].中兴通讯技术（英文版）,2022(03):61-69

subcarriers,subcar

Spectrum,Sensing,OFDMA,Using,Multicarrier,Covariance,Matrix,Aware,We,consider,spectrum,sensing,problems,orthogonal,frequency,division,multiplexing,access,cognitive,radio,where,secondary,antennas,detects,several,consecutive,entire,symbol,occupied,by,primary,users,Specifically,multicarrier,covariance,matrix,convolutional,neural,network,approach,proposed,simul,taneously,detecting,occupancy,sample,array,specially,set,input,efficiently,learn,energy,information,correlation,between,significantly,improve,performance,Numerical,results,demonstrate,that,has,substantial,advantage,over,state,art,methods,scenario,under,new

0.564245