TY - JOUR
T1 - Deep Learning-Aided Distributed Transmit Power Control for Underlay Cognitive Radio Network
AU - Lee, Woongsup
AU - Lee, Kisong
N1 - Publisher Copyright:
© 1967-2012 IEEE.
PY - 2021/4
Y1 - 2021/4
N2 - In this paper, we investigate deep learning-aided distributed transmit power control in the context of an underlay cognitive radio network (CRN). In the proposed scheme, the fully distributed transmit power control strategy of secondary users (SUs) is learned by means of a distributed deep neural network (DNN) structure in an unsupervised manner, such that the average spectral efficiency (SE) of the SUs is maximized whilst allowing the interference on primary users (PUs) to be regulated properly. Unlike previous centralized DNN-based strategies that require complete channel state information (CSI) to optimally determine the transmit power of SU transceiver pairs (TPs), in our proposed scheme, each SU TP determines its own transmit power based solely on its local CSI. Our simulation results verify that the proposed scheme can achieve a near-optimal SE comparable with a centralized DNN-based scheme, with a reduced computation time and no signaling overhead.
AB - In this paper, we investigate deep learning-aided distributed transmit power control in the context of an underlay cognitive radio network (CRN). In the proposed scheme, the fully distributed transmit power control strategy of secondary users (SUs) is learned by means of a distributed deep neural network (DNN) structure in an unsupervised manner, such that the average spectral efficiency (SE) of the SUs is maximized whilst allowing the interference on primary users (PUs) to be regulated properly. Unlike previous centralized DNN-based strategies that require complete channel state information (CSI) to optimally determine the transmit power of SU transceiver pairs (TPs), in our proposed scheme, each SU TP determines its own transmit power based solely on its local CSI. Our simulation results verify that the proposed scheme can achieve a near-optimal SE comparable with a centralized DNN-based scheme, with a reduced computation time and no signaling overhead.
KW - Deep neural network
KW - distributed operation
KW - transmit power control
KW - underlay cognitive radio network
UR - http://www.scopus.com/inward/record.url?scp=85103295200&partnerID=8YFLogxK
U2 - 10.1109/TVT.2021.3068368
DO - 10.1109/TVT.2021.3068368
M3 - Article
AN - SCOPUS:85103295200
SN - 0018-9545
VL - 70
SP - 3990
EP - 3994
JO - IEEE Transactions on Vehicular Technology
JF - IEEE Transactions on Vehicular Technology
IS - 4
M1 - 9384291
ER -