TY - JOUR
T1 - Learning-Based Adaptive IRS Control With Limited Feedback Codebooks
AU - Kim, Junghoon
AU - Hosseinalipour, Seyyedali
AU - Marcum, Andrew C.
AU - Kim, Taejoon
AU - Love, David J.
AU - Brinton, Christopher G.
N1 - Funding Information:
The work of Junghoon Kim, David J. Love, and Christopher G. Brinton was supported in part by the National Spectrum Consortium (NSC) under Grant W15QKN-15-9-1004, in part by the Office of Naval Research (ONR) under Grant N00014-21-1-2472, and in part by NSF CNS-2146171. The work of Taejoon Kim was supported in part by the National Science Foundation (NSF) under Grant CNS1955561.
Publisher Copyright:
© 2002-2012 IEEE.
PY - 2022/11/1
Y1 - 2022/11/1
N2 - Intelligent reflecting surfaces (IRS) consist of configurable meta-atoms, which can change the wireless propagation environment through design of their reflection coefficients. We consider a practical setting where (i) the IRS reflection coefficients are configured by adjusting tunable elements embedded in the meta-atoms, (ii) the IRS reflection coefficients are affected by the incident angles of the incoming signals, (iii) the IRS is deployed in multi-path, time-varying channels, and (iv) the feedback link from the base station to the IRS has a low data rate. Conventional optimization-based IRS control protocols, which rely on channel estimation and conveying the optimized variables to the IRS, are not applicable in this setting due to the difficulty of channel estimation and the low feedback rate. Therefore, we develop a novel adaptive codebook-based limited feedback protocol where only a codeword index is transferred to the IRS. We propose two solutions for adaptive codebook design, random adjacency (RA) and deep neural network policy-based IRS control (DPIC), both of which only require the end-to-end compound channels. We further develop several augmented schemes based on RA and DPIC. Numerical evaluations show that the data rate and average data rate over one coherence time are improved substantially by our schemes.
AB - Intelligent reflecting surfaces (IRS) consist of configurable meta-atoms, which can change the wireless propagation environment through design of their reflection coefficients. We consider a practical setting where (i) the IRS reflection coefficients are configured by adjusting tunable elements embedded in the meta-atoms, (ii) the IRS reflection coefficients are affected by the incident angles of the incoming signals, (iii) the IRS is deployed in multi-path, time-varying channels, and (iv) the feedback link from the base station to the IRS has a low data rate. Conventional optimization-based IRS control protocols, which rely on channel estimation and conveying the optimized variables to the IRS, are not applicable in this setting due to the difficulty of channel estimation and the low feedback rate. Therefore, we develop a novel adaptive codebook-based limited feedback protocol where only a codeword index is transferred to the IRS. We propose two solutions for adaptive codebook design, random adjacency (RA) and deep neural network policy-based IRS control (DPIC), both of which only require the end-to-end compound channels. We further develop several augmented schemes based on RA and DPIC. Numerical evaluations show that the data rate and average data rate over one coherence time are improved substantially by our schemes.
KW - Intelligent reflecting surface (IRS)
KW - adaptive codebook
KW - deep reinforcement learning
KW - limited feedback
KW - reconfigurable intelligent surface (RIS)
KW - software-controlled meta-surface
UR - http://www.scopus.com/inward/record.url?scp=85131751812&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85131751812&partnerID=8YFLogxK
U2 - 10.1109/TWC.2022.3178055
DO - 10.1109/TWC.2022.3178055
M3 - Article
AN - SCOPUS:85131751812
SN - 1536-1276
VL - 21
SP - 9566
EP - 9581
JO - IEEE Transactions on Wireless Communications
JF - IEEE Transactions on Wireless Communications
IS - 11
ER -