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.
|Number of pages||5|
|Journal||IEEE Transactions on Vehicular Technology|
|Publication status||Published - 2021 Apr|
Bibliographical noteFunding Information:
Manuscript received November 10, 2020; revised January 15, 2021; accepted March 15, 2021. Date of publication March 23, 2021; date of current version May 5, 2021. This work was supported in part by Basic Science Research Program through the National Research Foundation of Korea (NRF) funded by the Ministry of Education under Grant NRF-2018R1D1A1B07040796 and in part by the Korea government (MSIT) under Grant NRF-2021R1A2C4002024. The review of this article was coordinated by Prof. Z. Fadlullah. (Corresponding author: Kisong Lee.) Woongsup Lee is with the Department of Information and Communication Engineering, Institute of Marine Industry, Gyeongsang National University, Tongyoung 53064, South Korea (e-mail: email@example.com).
© 1967-2012 IEEE.
All Science Journal Classification (ASJC) codes
- Automotive Engineering
- Aerospace Engineering
- Electrical and Electronic Engineering
- Applied Mathematics