TY - JOUR
T1 - Dual-Propagation-Feature Fusion Enhanced Neural CSI Compression for Massive MIMO
AU - Zhang, Shaoqing
AU - Xu, Wei
AU - Jin, Shi
AU - You, Xiaohu
AU - Ng, Derrick Wing Kwan
AU - Wang, Li Chun
N1 - Publisher Copyright:
IEEE
PY - 2023
Y1 - 2023
N2 - 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.
AB - 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.
KW - Artificial neural networks
KW - channel state information (CSI)
KW - compression and reconstruction
KW - Deep learning
KW - Discrete Fourier transforms
KW - dual-feature fusion
KW - Feature extraction
KW - Image coding
KW - Image reconstruction
KW - Massive MIMO
KW - massive multiple-input multiple-output (MIMO)
KW - Quantization (signal)
UR - http://www.scopus.com/inward/record.url?scp=85161016422&partnerID=8YFLogxK
U2 - 10.1109/TCOMM.2023.3282227
DO - 10.1109/TCOMM.2023.3282227
M3 - Article
AN - SCOPUS:85161016422
SN - 0090-6778
SP - 1
JO - IEEE Transactions on Communications
JF - IEEE Transactions on Communications
ER -