Reconfigurable intelligent surfaces (RIS) are expected to play an important role in future wireless communication systems. These surfaces typically rely on their reflection beamforming codebooks to reflect and focus the signal on the target receivers. Prior work has mainly considered pre-defined RIS beamsteering codebooks that do not adapt to environment and hardware and lead to large beam training overhead. In this work, a novel deep reinforcement learning based framework is developed to efficiently construct the RIS reflection beam codebook. This framework adopts a multi-level design approach that transfers the learning between the multiple RIS subarrays, which speeds up the learning convergence and highly reduces the computational complexity for extremely large RIS surfaces. The proposed approach is generic for co-located/distributed RIS surfaces with arbitrary array geometries and with stationary/nonstationary channels. Further, the developed solution does not require explicitly channel knowledge and adapts the codebook beams to the surrounding environment, user distribution, and hardware characteristics. Simulation results show that the proposed learning framework can learn optimized interaction codebooks within reasonable iterations. Besides, with only 6 beams, the learned codebook outperforms a 256-beam DFT codebook, which significantly reduces the beam training overhead.
[1]
Richard Evans,et al.
Deep Reinforcement Learning in Large Discrete Action Spaces
,
2015,
1512.07679.
[2]
Ahmed Alkhateeb,et al.
DeepMIMO: A Generic Deep Learning Dataset for Millimeter Wave and Massive MIMO Applications
,
2019,
ArXiv.
[3]
Ahmed Alkhateeb,et al.
Reinforcement Learning of Beam Codebooks in Millimeter Wave and Terahertz MIMO Systems
,
2021,
IEEE Transactions on Communications.
[4]
Robert W. Heath,et al.
Non-Stationarities in Extra-Large-Scale Massive MIMO
,
2019,
IEEE Wireless Communications.
[5]
A. Lee Swindlehurst,et al.
Joint Symbol-Level Precoding and Reflecting Designs for IRS-Enhanced MU-MISO Systems
,
2019,
IEEE Transactions on Wireless Communications.
[6]
Xiaojun Yuan,et al.
Passive Beamforming and Information Transfer Design for Reconfigurable Intelligent Surfaces Aided Multiuser MIMO Systems
,
2019,
IEEE Journal on Selected Areas in Communications.
[7]
Ahmed Alkhateeb,et al.
Enabling Large Intelligent Surfaces With Compressive Sensing and Deep Learning
,
2019,
IEEE Access.
[8]
Amine Mezghani,et al.
Joint Active and Passive Beamforming Design for IRS-Assisted Multi-User MIMO Systems: A VAMP-Based Approach
,
2021,
IEEE Transactions on Communications.