Learning Representations for CSI Adaptive Quantization and Feedback
Abstract
The proposed method improves CSI quantization and feedback in FDD systems using advanced quantization techniques for autoencoder neural networks, enhancing reconstruction accuracy.
In this work, we propose an efficient method for channel state information (CSI) adaptive quantization and feedback in frequency division duplexing (FDD) systems. Existing works mainly focus on the implementation of autoencoder (AE) neural networks (NNs) for CSI compression, and consider straightforward quantization methods, e.g., uniform quantization, which are generally not optimal. With this strategy, it is hard to achieve a low reconstruction error, especially, when the available number of bits reserved for the latent space quantization is small. To address this issue, we recommend two different methods: one based on a post training quantization and the second one in which the codebook is found during the training of the AE. Both strategies achieve better reconstruction accuracy compared to standard quantization techniques.
Community
This preprint represents a preliminary study exploring ideas that were later developed further. For the final peer-reviewed article, see:
V. Rizzello, M. Nerini, M. Joham, B. Clerckx and W. Utschick, "User-Driven Adaptive CSI Feedback With Ordered Vector Quantization," in IEEE Wireless Communications Letters, vol. 12, no. 11, pp. 1956-1960, Nov. 2023, doi: 10.1109/LWC.2023.3301992.
Please cite the published version where appropriate. ๐ท
You can also explore the source code and read more in the related blog post.
Models citing this paper 0
No model linking this paper
Datasets citing this paper 0
No dataset linking this paper
Spaces citing this paper 0
No Space linking this paper
Collections including this paper 0
No Collection including this paper