.png){kind=icon}
Return
Implicit Neural Representations for Codebook Configuration in RIS-Aided Communication Systems
.png){kind=icon}
PRE
AI
DOI：10.1109/TCCN.2025.3633756.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Reconfigurable intelligent surface (RIS) is envisioned as a key enabling technology for 6G wireless communications. By configuring the reflection beamforming codebook, RIS focuses signals on target receivers to enhance signal strength. In this paper, we investigate the codebook configuration for both continuous-phase and 1-bit RIS-aided communication systems. We formulate an implicit relationship between user coordinates and the optimal codebook from the perspective of electromagnetic wave propagation mechanisms, and introduce a novel learning-based method, implicit neural representations (INRs), to solve this implicit coordinates-to-codebook mapping problem. Our approach requires only user coordinates, avoiding reliance on explicit channel models. For continuous-phase RIS, we introduce a phase normalization technique to address the periodicity and global phase offset challenges inherent in phase representation. Additionally, for the practical 1-bit RIS scenario, we formulate the codebook configuration as a multi-label classification problem and propose an encoding strategy to reduce codebook dimension, thereby improving learning efficiency. Experimental results from both simulated and real-world datasets demonstrate significant advantages of our unified method across both continuous and 1-bit codebook configurations. The datasets and code are available at: https://github.com/HUSTGSNeRF/Codebook_Inr
Keywords:
RIS
codebook configuration
implicit neural representations
phase normalization
multi-label classification
Journal
I
IF:
7
Papers:
1.6K
Citations:
5.5K
Organization
Cited Papers
.png){kind=icon}
ShareSaveShareSaveShareSaveShareSaveShareSaveSmart radio environments empowered by reconfigurable AI meta-surfaces: an idea whose time has come
OAAI
OAAIShareSave
View more