Skip to main navigation Skip to search Skip to main content

Dual-Propagation-Feature Fusion Enhanced Neural CSI Compression for Massive MIMO

  • Shaoqing Zhang
  • , Wei Xu*
  • , Shi Jin
  • , Xiaohu You
  • , Derrick Wing Kwan Ng
  • , Li Chun Wang
  • *Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

16 Scopus citations

Abstract

Due to the ability of feature extraction, deep learning (DL)-based methods have been recently applied to channel state information (CSI) compression feedback in massive multiple-input multiple-output (MIMO) systems. Existing DL-based CSI compression methods are usually effective in extracting a certain type of features in the CSI. However, the CSI usually contains two types of propagation features, i.g., non-line-of-sight (NLOS) propagation-path feature and dominant propagation-path feature, especially in channel environments with rich scatterers. To fully extract the both propagation features and learn a dual-feature representation for CSI, this paper proposes a dual-feature-fusion neural network (NN), referred to as DuffinNet. The proposed DuffinNet adopts a parallel structure with a convolutional neural network (CNN) and an attention-empowered neural network (ANN) to respectively extract different features in the CSI, and then explores their interplay by a fusion NN. Built upon this proposed DuffinNet, a new encoder-decoder framework is developed, referred to as Duffin-CsiNet, for improving the end-to-end performance of CSI compression and reconstruction. To facilitate the application of Duffin-CsiNet in practice, this paper also presents a two-stage approach for codeword quantization of the CSI feedback. Besides, a transfer learning-based strategy is introduced to improve the generalization of Duffin-CsiNet, which enables the network to be applied to new propagation environments. Simulation results illustrate that the proposed Duffin-CsiNet noticeably outperforms the existing DL-based methods in terms of reconstruction performance, encoder complexity, and network convergence, validating the effectiveness of the proposed dual-feature fusion design.

Original languageEnglish
Pages (from-to)5182-5198
Number of pages17
JournalIEEE Transactions on Communications
Volume71
Issue number9
DOIs
StatePublished - 1 Sep 2023

Keywords

  • Deep learning
  • channel state information (CSI)
  • compression and reconstruction
  • dual-feature fusion
  • massive multiple-input multiple-output (MIMO)

Fingerprint

Dive into the research topics of 'Dual-Propagation-Feature Fusion Enhanced Neural CSI Compression for Massive MIMO'. Together they form a unique fingerprint.

Cite this