Fully connected feedforward neural networks based CSI feedback algorithm

Gao, Ming; Liao, Tanming; Lu, Yubin

doi:10.23919/jcc.2021.01.004

Cited by 14 publications

(4 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The original CSI is represented by a basis and a residual part of the column space channel matrix; CF-FCFNN [48] The feedback NN architecture only consists of FC layers.…”

Section: Well-designed Preprocessingmentioning

confidence: 99%

“…b) Fully FC architecture: As mentioned in Section IV-A3, some works try to realize CSI feedback fully by convolutional layers. By contrast, a feedback NN architecture (called CF-FCFNN) in [48] only consists of FC layers. The CF-FCFNN architecture based on FC layers can extract spatial features more sufficiently compared with CsiNet based on convolutional layers and greatly outperforms CsiNet, especially when the feedback difficulty is high.…”

Section: Partial Bidirectional Channel Correlationmentioning

confidence: 99%

See 1 more Smart Citation

Overview of Deep Learning-based CSI Feedback in Massive MIMO Systems

Guo¹,

Wen²,

Jin³

et al. 2022

Preprint

View full text Add to dashboard Cite

Many performance gains achieved by massive multiple-input and multiple-output depend on the accuracy of the downlink channel state information (CSI) at the transmitter (base station), which is usually obtained by estimating at the receiver (user terminal) and feeding back to the transmitter. The overhead of CSI feedback occupies substantial uplink bandwidth resources, especially when the number of the transmit antennas is large. Deep learning (DL)-based CSI feedback refers to CSI compression and reconstruction by a DL-based autoencoder and can greatly reduce feedback overhead. In this paper, a comprehensive overview of state-of-the-art research on this topic is provided, beginning with basic DL concepts widely used in CSI feedback and then categorizing and describing some existing DL-based feedback works. The focus is on novel neural network architectures and utilization of communication expert knowledge to improve CSI feedback accuracy. Works on bitlevel CSI feedback and joint design of CSI feedback with other communication modules are also introduced, and some practical issues, including training dataset collection, online training, complexity, generalization, and standardization effect, are discussed. At the end of the paper, some challenges and potential research directions associated with DL-based CSI feedback in future wireless communication systems are identified.

show abstract

“…The original CSI is represented by a basis and a residual part of the column space channel matrix; CF-FCFNN [48] The feedback NN architecture only consists of FC layers.…”

Section: Well-designed Preprocessingmentioning

confidence: 99%

Section: Partial Bidirectional Channel Correlationmentioning

confidence: 99%

Overview of Deep Learning-based CSI Feedback in Massive MIMO Systems

Guo¹,

Wen²,

Jin³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…And reconstruct the downlink CSI at the BS with the noise feedback link to improve the acquisition performance under the noise feedback. Reference [26] proposed a CSI feedback framework CF-FCFNN based on a fully connected forward neural network. This framework can significantly improve channel quality without increasing time complexity and obtain better system performance.…”

Section: Related Workmentioning

confidence: 99%

Channel state information acquisition method of internet of things based on deep learning

Zhang¹

2021

The Journal of Engineering

View full text Add to dashboard Cite

As one of the key technologies of Internet of things (IoT), the accurate and efficient acquisition of CSI is an important part to support the high quality communication of IOT system. However, the current IOT system is massive and complex, and the traditional CSI acquisition method is difficult to meet its efficient information communication. To solve this problem, this paper proposes an improved CSI acquisition method based on bidirectional convolutional long and short-term memory networks (Bidirectional Convolutional Long Short-Term Memory, Bi-ConvLSTM) and attention mechanism. This method unifies the Bi-ConvLSTM-Attention network module to improve the encoder and decoder of the CSI-Net network model. Among them, the Bi-ConvLSTM module is mainly used to learn the time correlation between channel matrices. The attention mechanism module is used to calculate the soft probability distribution, so that the Bi-ConvLSTM network has the function of automatic weighting, thereby further improving the characterization ability of characteristic information. In the last part of the thesis, the proposed method is simulated and verified. Experimental results show that the proposed method exhibits excellent network performance in both single-user and multi-user massive MIMO system scenarios. Compared with the comparison method, the bit error rate performance and system capacity are improved by about 0.3-6 dB and 1.3-3.7 bps/Hz in the multi-user complex scene.

show abstract

“…By employing a machine learning approach, it is possible to design a wireless physical layer [11][12][13], feedback method of CSI depending on deep learning technique for massive MIMO has been implemented, where convolutional neural networks convert the indices of the channels to receiver's compressed expressions and then inverse transformation is performed on transmitter side [14,15]. Comparable to mentioned techniques, the channel is considered sparse, which isn't a universal assumption; for example, it's not appropriate for a dynamic dispersed ecosystem.…”

Section: Introductionmentioning

confidence: 99%

Massive MIMO Codebook Design Using Gaussian Mixture Model Based Clustering

Markkandan¹,

Sivasubramanian²,

Mulerikkal³

et al. 2022

Intelligent Automation &Amp; Soft Computing

View full text Add to dashboard Cite

The codebook design is the most essential core technique in constrained feedback massive multi-input multi-output (MIMO) system communications. MIMO vectors have been generally isotropic or evenly distributed in traditional codebook designs. In this paper, Gaussian mixture model (GMM) based clustering codebook design is proposed, which is inspired by the strong classification and analytical abilities of clustering techniques. Huge quantities of channel state information (CSI) are initially saved as entry data of the clustering process. Further, split into N number of clusters based on the shortest distance. The centroids part of clustering has been utilized for constructing a codebook with statistic channel information, with an average distance that is the shortest towards the true channel data. The enhanced GMM based clustering codebook design outperforms traditional methods, particularly in the situations of non-uniform distribution of channels as demonstrated via simulation results which match theoretical analyses concerning achievable rate. The proposed GMM based clustering codebook design is compared with DFT-based clustering codebook design and k-means based clustering codebook design.

show abstract

Fully connected feedforward neural networks based CSI feedback algorithm

Cited by 14 publications

References 16 publications

Overview of Deep Learning-based CSI Feedback in Massive MIMO Systems

Overview of Deep Learning-based CSI Feedback in Massive MIMO Systems

Channel state information acquisition method of internet of things based on deep learning

Massive MIMO Codebook Design Using Gaussian Mixture Model Based Clustering

Contact Info

Product

Resources

About