TY - GEN
T1 - The Application of Machine Learning in mmWave-NOMA Systems
AU - Cui, Jingjing
AU - Ding, Zhiguo
AU - Fan, Pingzhi
N1 - Funding Information:
ACKNOWLEDGEMENT The work of Jingjing Cui and Pingzhi Fan was supported by NSFC key project under grant No.61731017, the National Science and Technology Major Project under Grant No.2016ZX03001018, and the 111 Project under Grant No.111-2-1.
Publisher Copyright:
© 2018 IEEE.
PY - 2018/7/20
Y1 - 2018/7/20
N2 - Machine learning has been used to develop efficiently optimizing algorithms for practical communication systems. This paper investigates the user clustering and power allocation problem in the millimeter wave non- orthogonal multiple access (mmWave-NOMA) transmission scenario, where we assume that the users' locations of different clusters follows a Poisson cluster process (PCP). Specifically, we develop a machine learning based user clustering algorithm for the application of NOMA. Moreover, to investigate the performance of the proposed mmWave-NOMA system, we derive the optimal power allocation coefficients in closed-form by assuming equal power on each beam. In the simulation results, we firstly investigate the impact of the number of clusters on the system performance. We further show the validation of the proposed machine-learning based user clustering algorithm in the mmWave-NOMA system.
AB - Machine learning has been used to develop efficiently optimizing algorithms for practical communication systems. This paper investigates the user clustering and power allocation problem in the millimeter wave non- orthogonal multiple access (mmWave-NOMA) transmission scenario, where we assume that the users' locations of different clusters follows a Poisson cluster process (PCP). Specifically, we develop a machine learning based user clustering algorithm for the application of NOMA. Moreover, to investigate the performance of the proposed mmWave-NOMA system, we derive the optimal power allocation coefficients in closed-form by assuming equal power on each beam. In the simulation results, we firstly investigate the impact of the number of clusters on the system performance. We further show the validation of the proposed machine-learning based user clustering algorithm in the mmWave-NOMA system.
UR - http://www.scopus.com/inward/record.url?scp=85050976723&partnerID=8YFLogxK
U2 - 10.1109/VTCSpring.2018.8417523
DO - 10.1109/VTCSpring.2018.8417523
M3 - Conference contribution
AN - SCOPUS:85050976723
T3 - IEEE Vehicular Technology Conference
SP - 1
EP - 6
BT - 2018 IEEE 87th Vehicular Technology Conference, VTC Spring 2018 - Proceedings
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 87th IEEE Vehicular Technology Conference, VTC Spring 2018
Y2 - 3 June 2018 through 6 June 2018
ER -