Limited Feedback on Measurements: Sharing a Codebook or a Generative Model?

TL;DR

The paper tackles limited feedback in FDD MU-MIMO by comparing traditional DFT-codebook approaches with a GMM-based, environment-aware feedback scheme trained on real-world measurements. It introduces offline GMM fitting to model the BS-cell environment, structured covariance to ease model transfer to MTs, online pilot-based inference to select a GMM component, and two precoding paths: directional information-based and generative modeling-based via SWMMSE. Real-world data from a Nokia campus measurement campaign show that the GMM-based feedback yields large sum-rate gains, especially at low pilot overhead, with further improvements when employing generative precoding. These results demonstrate that sharing a generative model across BS and MTs can reduce pilot/feedback requirements while delivering robust performance, suggesting strong potential for practical deployment in 6G-scale MIMO systems.

Abstract

Discrete Fourier transform (DFT) codebook-based solutions are well-established for limited feedback schemes in frequency division duplex (FDD) systems. In recent years, data-aided solutions have been shown to achieve higher performance, enabled by the adaptivity of the feedback scheme to the propagation environment of the base station (BS) cell. In particular, a versatile limited feedback scheme utilizing Gaussian mixture models (GMMs) was recently introduced. The scheme supports multi-user communications, exhibits low complexity, supports parallelization, and offers significant flexibility concerning various system parameters. Conceptually, a GMM captures environment knowledge and is subsequently transferred to the mobile terminals (MTs) for online inference of feedback information. Afterward, the BS designs precoders using either directional information or a generative modeling-based approach. A major shortcoming of recent works is that the assessed system performance is only evaluated through synthetic simulation data that is generally unable to fully characterize the features of real-world environments. It raises the question of how the GMM-based feedback scheme performs on real-world measurement data, especially compared to the well-established DFT-based solution. Our experiments reveal that the GMM-based feedback scheme tremendously improves the system performance measured in terms of sum-rate, allowing to deploy systems with fewer pilots or feedback bits.

Figures (6)

• Figure 1: Nokia campus in Stuttgart, Germany---Measurement environment.
• Figure 2: The sum-rate over the SNR for a system with $B=6$ feedback bits, $J=8$MT, and $n_p=8$ pilots.
• Figure 3: The sum-rate over the number $n_p$ of pilots for a system with $J=8$MT, and $\text{SNR}=10dB$.
• Figure 4: The sum-rate over the number $B$ of feedback bits for a system with $J=8$MT, $n_p=8$ pilots, and $\text{SNR}=10dB$.
• Figure 5: The sum-rate over the number $J$ of MT for a system with $B=6$ feedback bits, $n_p=16$ pilots, and $\text{SNR}=10dB$.