TY - JOUR
T1 - Deep Learning for Massive MiMO with 1-Bit ADCs
T2 - When More Antennas Need Fewer Pilots
AU - Zhang, Yu
AU - Alrabeiah, Muhammad
AU - Alkhateeb, Ahmed
N1 - Funding Information:
Manuscript received March 23, 2020; accepted April 4, 2020. Date of publication April 14, 2020; date of current version August 7, 2020. This work was supported by the National Science Foundation under Grant 1923676. The associate editor coordinating the review of this article and approving it for publication was C.-K. Wen. (Corresponding author: Ahmed Alkhateeb.) The authors are with the School of Electrical, Computer and Energy Engineering, Arizona State University, Tempe, AZ 85287 USA (e-mail: y.zhang@asu.edu; malrabei@asu.edu; alkhateeb@asu.edu). Digital Object Identifier 10.1109/LWC.2020.2987893
Publisher Copyright:
© 2012 IEEE.
PY - 2020/8
Y1 - 2020/8
N2 - This letter considers uplink massive MiMO systems with 1-bit analog-to-digital converters (ADCs) and develops a deep-learning based channel estimation framework. In this framework, the prior channel estimation observations and deep neural networks are leveraged to learn the non-trivial mapping from quantized received measurements to channels. For that, we derive the sufficient length and structure of the pilot sequence to guarantee the existence of this mapping function. This leads to the Interesting, and counter-intuitive, observation that when more base-station antennas are employed, our proposed deep learning approach achieves better channel estimation performance, for the same pilot sequence length. Equivalently, for the same channel estimation performance, this means that when more antennas are employed, fewer pilots are required. This observation Is also analytically proved for some special channel models. Simulation results confirm our observations and show that more antennas lead to better channel estimation In terms of the normalized mean squared error and the receive signal-to-noise ratio per antenna.
AB - This letter considers uplink massive MiMO systems with 1-bit analog-to-digital converters (ADCs) and develops a deep-learning based channel estimation framework. In this framework, the prior channel estimation observations and deep neural networks are leveraged to learn the non-trivial mapping from quantized received measurements to channels. For that, we derive the sufficient length and structure of the pilot sequence to guarantee the existence of this mapping function. This leads to the Interesting, and counter-intuitive, observation that when more base-station antennas are employed, our proposed deep learning approach achieves better channel estimation performance, for the same pilot sequence length. Equivalently, for the same channel estimation performance, this means that when more antennas are employed, fewer pilots are required. This observation Is also analytically proved for some special channel models. Simulation results confirm our observations and show that more antennas lead to better channel estimation In terms of the normalized mean squared error and the receive signal-to-noise ratio per antenna.
KW - 1-bit ADCs
KW - Deep learning
KW - channel estimation
KW - massive MiMO
UR - http://www.scopus.com/inward/record.url?scp=85085857483&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85085857483&partnerID=8YFLogxK
U2 - 10.1109/LWC.2020.2987893
DO - 10.1109/LWC.2020.2987893
M3 - Article
AN - SCOPUS:85085857483
SN - 2162-2337
VL - 9
SP - 1273
EP - 1277
JO - IEEE Wireless Communications Letters
JF - IEEE Wireless Communications Letters
IS - 8
M1 - 9067011
ER -