Skip to content
DraconiticResearch
Search Sources API
189,273 studies31 sourcesUpdated 49 min ago
PreprintarXiv licencearXiv

GNN-Based Global CSI Reconstruction for Fronthaul-Limited Distributed MIMO Systems

  • Haojin Li
  • Kaiqian Qu
  • Anbang Zhang
  • Chen Sun
  • Wenqi Zhang
  • Haijun Zhang
Open at sourcePDFDOICite

Abstract

Global channel state information (CSI) acquisition is essential for cooperative precoding in distributed multiple-input multiple-output (DMIMO) systems, but uploading full instantaneous CSI from all distributed antennas creates heavy fronthaul overhead. This paper proposes a fronthaul-efficient acquisition framework based on graph neural network (GNN) reconstruction and task-driven antenna selection. Each transmission and reception point (TRP) uploads only selected antenna CSI, while the centralized unit (CU) reconstructs the full global CSI from partial observations. A universal mask-conditioned GNN is trained with random upload masks, used to evaluate antenna subsets under a fronthaul budget, and then fine-tuned for the selected deployment mask. Simulation results show improved CSI reconstruction accuracy with lower fronthaul and pilot overhead.

Related

  1. Scalable Distortion-Aware Clustering for Fronthaul-Limited Cell-Free MIMO Networks
    Zehua Li, Raviraj Adve, Israfil Bahceci +1
    arXivPreprintCC BY 4.0Full textOptimisation & controlarXiv
  2. Optimizing diffusion-limited transport, with applications to electrochemical systems
    Manu Mannattil, L. Mahadevan
    arXivPreprintarXiv licenceFull textPhysical chemistryOptimisation & controlarXiv
  3. Provably Safe Decentralized Contingency MPC under State-Only Information and Limited Sensing for Nonlinear Multi-agent Systems
    Max Studt, Georg Schildbach
    arXivPreprintCC BY 4.0Full textOptimisation & controlarXiv
  4. Non-Uniform Activation Aided Distributed Generalized Spatial Modulation for DMIMO Systems
    Haojin Li, Chen Sun, Rang Su +3
    arXivPreprintarXiv licenceFull textGeneral mathematicsarXiv
  5. Bistatic Delay-Doppler Sensing for 3D Target Localization in Distributed Wi-Fi Systems
    Kyungmin Hong, Moein Ahmadi, Thomas Stifter +2
    arXivPreprintarXiv licenceFull textGeneral mathematicsarXiv

Cite

BibTeXRIS
BibTeX
@misc{li2026gnnbased,
  title = {{GNN-Based Global CSI Reconstruction for Fronthaul-Limited Distributed MIMO Systems}},
  author = {Haojin Li and Kaiqian Qu and Anbang Zhang and Chen Sun and Wenqi Zhang and Haijun Zhang},
  howpublished = {arXiv},
  year = {2026},
  month = sep,
  doi = {10.48550/arxiv.2609.23365},
  eprint = {2609.23365},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2609.23365},
}
RIS
TY  - UNPB
TI  - GNN-Based Global CSI Reconstruction for Fronthaul-Limited Distributed MIMO Systems
AU  - Haojin Li
AU  - Kaiqian Qu
AU  - Anbang Zhang
AU  - Chen Sun
AU  - Wenqi Zhang
AU  - Haijun Zhang
PY  - 2026
DA  - 2026/09/20
PB  - arXiv
DO  - 10.48550/arxiv.2609.23365
UR  - https://arxiv.org/abs/2609.23365
AB  - Global channel state information (CSI) acquisition is essential for cooperative precoding in distributed multiple-input multiple-output (DMIMO) systems, but uploading full instantaneous CSI from all distributed antennas creates heavy fronthaul overhead. This paper proposes a fronthaul-efficient acquisition framework based on graph neural network (GNN) reconstruction and task-driven antenna selection. Each transmission and reception point (TRP) uploads only selected antenna CSI, while the centralized unit (CU) reconstructs the full global CSI from partial observations. A universal mask-conditioned GNN is trained with random upload masks, used to evaluate antenna subsets under a fronthaul budget, and then fine-tuned for the selected deployment mask. Simulation results show improved CSI reconstruction accuracy with lower fronthaul and pilot overhead.
ER  -