TechRxiv

Dynamic Conjugate Gradient Unfolding for Symbol Detection in Time-Varying Massive MIMO

Download (687.49 kB)
preprint
posted on 2023-12-04, 03:39 authored by Toluwaleke OlutayoToluwaleke Olutayo, Benoit Champagne

This work addresses symbol detection in timevarying Massive Multiple-Input Multiple-Output (M-MIMO) systems. While conventional symbol detection techniques often exhibit subpar performance or impose significant computational burdens in such systems, learning-based methods have shown potential in stationary scenarios but often struggle to adapt to nonstationary conditions. To address these challenges, we introduce a hierarchy of extensions to the Learned Conjugate Gradient Network (LcgNet) M-MIMO detector. Firstly, we present Preconditioned LcgNet (PrLcgNet), which incorporates a preconditioner during training to enhance the uplink M-MIMO detector’s filter matrix. This enhancement enables the detector to achieve faster convergence with fewer layers compared to the original, nonpreconditioned approach. Secondly, we introduce an extension of PrLcgNet, known as the Dynamic Conjugate Gradient Network (DyCoGNet), specifically designed for time-varying environments. DyCoGNet leverages self-supervised learning with forward error correction, enabling autonomous adaptation without the need for explicit labeled data during training. It also employs metalearning, facilitating rapid adaptation to unforeseen channel conditions. Our simulation results demonstrate that PrLcgNet achieves faster convergence, lower residual error, and comparable symbol error rate (SER) performance to LcgNet in stationary scenarios. Furthermore, in the time-varying context, DyCoGNet exhibits swift and efficient adaptation, achieving significant SER performance gains compared to baseline cases without metalearning and online self-supervised learning.

History

Email Address of Submitting Author

toluwaleke.olutayo@mail.mcgill.ca

ORCID of Submitting Author

0009-0002-9755-540X

Submitting Author's Institution

McGill University

Submitting Author's Country

  • Canada

Usage metrics

    Licence

    Exports

    RefWorks
    BibTeX
    Ref. manager
    Endnote
    DataCite
    NLM
    DC