Deep Learning and Compressive Sensing-Based CSI Feedback in FDD Massive MIMO Systems

Liang, Peizhe; Fan, Jiancun; Shen, Wenhan; Qin, Zhijin; Li, Geoffrey Ye

doi:10.1109/tvt.2020.3004842

Cited by 64 publications

(24 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Authors explained different CS models, and in particular discussed how CS can play an instrumental role for the three different technical domains vis higher spectral efficiency, larger transmission bandwidth and efficient spectrum reuse. Liang et al [230] proposed to solve the problem of BS getting overwhelmed by the estimates of downlink CSI. These estimates are necessary for efficient working of FDD-MIMO systems and are computed at UEs to send to BS.…”

Section: Compressive Sensingmentioning

confidence: 99%

Survey on 6G Frontiers: Trends, Applications, Requirements, Technologies and Future Research

Alwis

Kalla

Pham

et al. 2021

IEEE Open J. Commun. Soc.

369

162

View full text Add to dashboard Cite

Emerging applications such as Internet of Everything, Holographic Telepresence, collaborative robots, and space and deep-sea tourism are already highlighting the limitations of existing fifth-generation (5G) mobile networks. These limitations are in terms of data-rate, latency, reliability, availability, processing, connection density and global coverage, spanning over ground, underwater and space. The sixth-generation (6G) of mobile networks are expected to burgeon in the coming decade to address these limitations. The development of 6G vision, applications, technologies and standards has already become a popular research theme in academia and the industry. In this paper, we provide a comprehensive survey of the current developments towards 6G. We highlight the societal and technological trends that initiate the drive towards 6G. Emerging applications to realize the demands raised by 6G driving trends are discussed subsequently. We also elaborate the requirements that are necessary to realize the 6G applications. Then we present the key enabling technologies in detail. We also outline current research projects and activities including standardization efforts towards the development of 6G. Finally, we summarize lessons learned from state-of-the-art research and discuss technical challenges that would shed a new light on future research directions towards 6G.

show abstract

Section: Compressive Sensingmentioning

confidence: 99%

Survey on 6G Frontiers: Trends, Applications, Requirements, Technologies and Future Research

Alwis

Kalla

Pham

et al. 2021

IEEE Open J. Commun. Soc.

369

162

View full text Add to dashboard Cite

show abstract

“…ML-based channel estimation using the denoising methods is proposed in [83][84][85][86][87][88]. In [83], the beamspace mmWave massive MIMO channel matrix is treated as a 2D image, where a learned denoising-based approximate message passing (LDAMP) NN integrating denoising CNN estimates the mmWave channel by subtracting the estimated residual noise from the noisy channel.…”

Section: Ml-based Solutionsmentioning

confidence: 99%

Acquisition of channel state information for mmWave massive MIMO: traditional and machine learning-based approaches

Dong

et al. 2021

Sci. China Inf. Sci.

Self Cite

View full text Add to dashboard Cite

The accuracy of channel state information (CSI) acquisition directly affects the performance of millimeter wave (mmWave) communications. In this article, we provide an overview on CSI acquisition, including beam training and channel estimation for mmWave massive multiple-input multiple-output systems. The beam training can avoid the estimation of a high-dimension channel matrix, while the channel estimation can flexibly exploit advanced signal processing techniques. In addition to introducing the traditional and machine learning-based approaches in this article, we also compare different approaches in terms of spectral efficiency, computational complexity, and overhead.

show abstract

“…By choosing the first N s rows of e H, we can reduce the dimension of datasets and the training time. We applied the encoder and decoder of CsiNet [16,17] to build CNN1 and CNN2, respectively. The architectures are shown in Fig.…”

Section: Cnn Network Structure and Trainingmentioning

confidence: 99%

“…Considering the sparsity of massive MIMO channels in the angular-delay domain, we first use 2D-DFT to convert the spatial-frequency domain into the angular-delay domain, aiming to reduce the complexity and difficulty of feature extraction [16,17]. Specifically, we obtain H as:…”

Section: Cnn Network Structure and Trainingmentioning

confidence: 99%

Convolutional Neural Network and Clustering-Based Codebook Design Method for Massive MIMO Systems

Xing

2021

Preprint

View full text Add to dashboard Cite

In this paper, we propose a convolutional neural network(CNN) and clustering based codebook design method. Specifically, we train two different CNN networks, i.e., CNN1 and CNN2, to compress the channel state information(CSI) matrices into the channel vectors and recover the channel vectors back into the CSI matrices, respectively. After that, the clustering algorithm clusters the output of CNN1, i.e., the channel vectors into several clusters and outputs a centroid for each cluster. The sum-distance between each centroid and the channel vectors in the corresponding cluster is the smallest, which can lead to the maximum sum-rate of massive MIMO codebook design. Then, the centroids are recovered into matrices by CNN2. The output of CNN2 is our proposed codebook for massive multiple-input multiple-output(MIMO) systems. In the simulation, we compare the performance of different clustering algorithms. We also compare the proposed codebook with the traditional Discrete Fourier Transform(DFT) codebook. Simulation results show the superiority of the proposed algorithm.

show abstract

Deep Learning and Compressive Sensing-Based CSI Feedback in FDD Massive MIMO Systems

Cited by 64 publications

References 29 publications

Survey on 6G Frontiers: Trends, Applications, Requirements, Technologies and Future Research

Survey on 6G Frontiers: Trends, Applications, Requirements, Technologies and Future Research

Acquisition of channel state information for mmWave massive MIMO: traditional and machine learning-based approaches

Convolutional Neural Network and Clustering-Based Codebook Design Method for Massive MIMO Systems

Contact Info

Product

Resources

About