Learning Reflection Beamforming Codebooks for Arbitrary RIS and Non-Stationary Channels

LIS_main_fig_final_v2

A mmWave/THz base station is communicating with multiple users via a distributed RIS using an interaction (beamforming) codebook.

Key ideas

  • Proposing a multi-level reflection design process to reduce the ultra high computational complexity associated with the extremely large RIS surfaces
  • Transferring the knowledge across the subarrays to speed up the convergence as well as to reduce the computational complexity
  • Adapting the reflection beamforming codebooks to the non-stationary channels and arbitrary RIS geometries

Applications

  • Learning reflection codebooks for co-located/distributed RIS surfaces
  • Learning reflection codebooks that adapt to the surrounding radio propagation environments and user distributions
  • Enabling fast codebook adaptation in the highly dynamic environments

More information about this research direction

Paper: Yu Zhang and Ahmed Alkhateeb, “Learning Reflection Beamforming Codebooks for Arbitrary RIS and Non-Stationary Channels,” arXiv preprint arXiv:2109.14909 (2021).

Abstract: 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 the 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 large RIS surfaces. The proposed approach is generic for co-located/distributed RIS surfaces with arbitrary array geometries and with stationary/non-stationary 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.

@misc{Zhang2021,
title={Learning Reflection Beamforming Codebooks for Arbitrary RIS and Non-Stationary Channels},
author={Yu Zhang and Ahmed Alkhateeb},
year={2021},
eprint={2109.14909},
archivePrefix={arXiv},
primaryClass={cs.IT}}

To reproduce the results in this paper:

Simulation codes:
These simulations use the DeepMIMO scenarios:
Example: Steps to generate the results in this figure
  1. Follow the detailed instructions provided in the above GitHub repo.

Having questions or feedback?

Send an email to 

 

Or post your question in the DeepMIMO forum