Universal Auto-encoder Framework for MIMO CSI Feedback
This work addresses a practical issue in wireless communication for user equipment with limited hardware resources, though it is incremental as it builds on existing auto-encoder approaches.
The paper tackles the problem of channel state information (CSI) feedback in MIMO systems, where existing auto-encoder frameworks are limited to fixed input and output sizes, by proposing a universal auto-encoder framework that supports variable sizes and multiple compression ratios, achieving comparable performance to state-of-the-art methods while reducing hardware complexity.
Existing auto-encoder (AE)-based channel state information (CSI) frameworks have focused on a specific configuration of user equipment (UE) and base station (BS), and thus the input and output sizes of the AE are fixed. However, in the real-world scenario, the input and output sizes may vary depending on the number of antennas of the BS and UE and the allocated resource block in the frequency dimension. A naive approach to support the different input and output sizes is to use multiple AE models, which is impractical for the UE due to the limited HW resources. In this paper, we propose a universal AE framework that can support different input sizes and multiple compression ratios. The proposed AE framework significantly reduces the HW complexity while providing comparable performance in terms of compression ratio-distortion trade-off compared to the naive and state-of-the-art approaches.