TY - GEN
T1 - Deep Reinforcement Learning for Intelligent Reflecting Surfaces
T2 - 21st IEEE International Workshop on Signal Processing Advances in Wireless Communications, SPAWC 2020
AU - Taha, Abdelrahman
AU - Zhang, Yu
AU - Mismar, Faris B.
AU - Alkhateeb, Ahmed
N1 - Publisher Copyright:
© 2020 IEEE.
PY - 2020/5
Y1 - 2020/5
N2 - The promising coverage and spectral efficiency gains of intelligent reflecting surfaces (IRSs) are attracting increasing interest. To adopt these surfaces in practice, however, several challenges need to be addressed. One of these main challenges is how to configure the reflecting coefficients on these passive surfaces without requiring massive channel estimation or beam training overhead. Earlier work suggested leveraging supervised learning tools to predict the IRS reflection matrices. While this approach has the potential of reducing the beam training overhead, it requires collecting large datasets for training the neural network models. In this paper, we propose a novel deep reinforcement learning framework for predicting the IRS reflection matrices with minimal beam training overhead. Simulation results show that the proposed online learning framework can converge to the optimal rate that assumes perfect channel knowledge. This represents an important step towards realizing a standalone IRS operation, where the surface configures itself without any control from the infrastructure.
AB - The promising coverage and spectral efficiency gains of intelligent reflecting surfaces (IRSs) are attracting increasing interest. To adopt these surfaces in practice, however, several challenges need to be addressed. One of these main challenges is how to configure the reflecting coefficients on these passive surfaces without requiring massive channel estimation or beam training overhead. Earlier work suggested leveraging supervised learning tools to predict the IRS reflection matrices. While this approach has the potential of reducing the beam training overhead, it requires collecting large datasets for training the neural network models. In this paper, we propose a novel deep reinforcement learning framework for predicting the IRS reflection matrices with minimal beam training overhead. Simulation results show that the proposed online learning framework can converge to the optimal rate that assumes perfect channel knowledge. This represents an important step towards realizing a standalone IRS operation, where the surface configures itself without any control from the infrastructure.
KW - beamforming
KW - deep reinforcement learning
KW - intelligent reflecting surface
KW - large intelligent surface
KW - reconfigurable intelligent surface
KW - smart reflect-Array
UR - http://www.scopus.com/inward/record.url?scp=85090395214&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85090395214&partnerID=8YFLogxK
U2 - 10.1109/SPAWC48557.2020.9154301
DO - 10.1109/SPAWC48557.2020.9154301
M3 - Conference contribution
AN - SCOPUS:85090395214
T3 - IEEE Workshop on Signal Processing Advances in Wireless Communications, SPAWC
BT - 2020 IEEE 21st International Workshop on Signal Processing Advances in Wireless Communications, SPAWC 2020
PB - Institute of Electrical and Electronics Engineers Inc.
Y2 - 26 May 2020 through 29 May 2020
ER -