TY - GEN
T1 - Generative Adversarial Estimation of Channel Covariance in Vehicular Millimeter Wave Systems
AU - Li, Xiaofeng
AU - Alkhateeb, Ahmed
AU - Tepedelenlioglu, Cihan
N1 - Publisher Copyright:
© 2018 IEEE.
PY - 2018/7/2
Y1 - 2018/7/2
N2 - Enabling highly-mobile millimeter wave (mmWave) systems is challenging because of the huge training overhead associated with acquiring the channel knowledge or designing the narrow beams. Current mmWave beam training and channel estimation techniques do not normally make use of the prior beam training or channel estimation observations. Intuitively, though, the channel matrices are functions of the various elements of the environment. Learning these functions can dramatically reduce the training overhead needed to obtain the channel knowledge. In this paper, a novel solution that exploits machine learning tools, namely conditional generative adversarial networks (GAN), is developed to learn these functions between the environment and the channel covariance matrices. More specifically, the proposed machine learning model treats the covariance matrices as 2D images and learns the mapping function relating the uplink received pilots, which act as RF signatures of the environment, and these images. Simulation results show that the developed strategy efficiently predicts the covariance matrices of the large-dimensional mmWave channels with negligible training overhead.
AB - Enabling highly-mobile millimeter wave (mmWave) systems is challenging because of the huge training overhead associated with acquiring the channel knowledge or designing the narrow beams. Current mmWave beam training and channel estimation techniques do not normally make use of the prior beam training or channel estimation observations. Intuitively, though, the channel matrices are functions of the various elements of the environment. Learning these functions can dramatically reduce the training overhead needed to obtain the channel knowledge. In this paper, a novel solution that exploits machine learning tools, namely conditional generative adversarial networks (GAN), is developed to learn these functions between the environment and the channel covariance matrices. More specifically, the proposed machine learning model treats the covariance matrices as 2D images and learns the mapping function relating the uplink received pilots, which act as RF signatures of the environment, and these images. Simulation results show that the developed strategy efficiently predicts the covariance matrices of the large-dimensional mmWave channels with negligible training overhead.
UR - http://www.scopus.com/inward/record.url?scp=85062968722&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85062968722&partnerID=8YFLogxK
U2 - 10.1109/ACSSC.2018.8645463
DO - 10.1109/ACSSC.2018.8645463
M3 - Conference contribution
AN - SCOPUS:85062968722
T3 - Conference Record - Asilomar Conference on Signals, Systems and Computers
SP - 1572
EP - 1576
BT - Conference Record of the 52nd Asilomar Conference on Signals, Systems and Computers, ACSSC 2018
A2 - Matthews, Michael B.
PB - IEEE Computer Society
T2 - 52nd Asilomar Conference on Signals, Systems and Computers, ACSSC 2018
Y2 - 28 October 2018 through 31 October 2018
ER -