Sparse Bayesian Learning Kalman Filter-based Channel Estimation for Hybrid Millimeter Wave MIMO Systems: A Frequency Domain Approach

K, Shoukath Ali; Sampath, P.

doi:10.1080/03772063.2021.1951367

Cited by 10 publications

(1 citation statement)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Moreover, Orthogonal Matching Pursuit (OMP) is deemed a good candidate for designing hybrid precoders. However, with the increment in the number of transceivers, the computational complexity gets increased in OMP [19,20]. As a result, it brings a poor estimation of the channel matrix due to the increment in the computational complexity, which reduces the spectral efficiency.…”

Section: Introductionmentioning

confidence: 99%

Learned-SBL-GAMP based hybrid precoders/combiners in millimeter wave massive MIMO systems

Ali K.,

Khan,

et al. 2023

PLoS ONE

View full text Add to dashboard Cite

In Millimeter-Wave (mm-Wave) massive Multiple-Input Multiple-Output (MIMO) systems, hybrid precoders/combiners must be designed to improve antenna gain and reduce hardware complexity. Sparse Bayesian learning via Expectation Maximization (SBL-EM) algorithm is not practically feasible for high signal dimensions because estimating sparse signals and designing optimal hybrid precoders/combiners using SBL-EM still provide high computational complexity for higher signal dimensions. To overcome the issues of high computational complexity along with making it suitable for larger data sets, in this paper, we propose Learned-Sparse Bayesian Learning with Generalized Approximate Message Passing algorithm (L-SBL-GAMP) algorithm for designing optimal hybrid precoders/combiners suitable for mmWave Massive MIMO systems. The L-SBL-GAMP algorithm is an extension of the SBL-GAMP algorithm that incorporates a Deep Neural Network (DNN) to improve the system performance. Based on the nature of the training data, the L-SBL-GAMP can design the optimal Hybrid precoders/combiners, which enhances the spectral efficiency of mmWave massive MIMO systems. The proposed L-SBL-GAMP algorithm reduces the iterations, training overhead, and computational complexity compared to the SBL-EM algorithm. The simulation results unveil that the proposed L-SBL-GAMP provides higher achievable rates, better accuracy, and low computational complexity compared to the existing algorithm, such as Orthogonal Matching Pursuit (OMP), Simultaneous Orthogonal Matching Pursuit (SOMP), SBL-EM and SBL-GAMP for mmWave massive MIMO architectures.

show abstract

Section: Introductionmentioning

confidence: 99%

Learned-SBL-GAMP based hybrid precoders/combiners in millimeter wave massive MIMO systems

Ali K.,

Khan,

et al. 2023

PLoS ONE

View full text Add to dashboard Cite

show abstract

Gaussian Mixture—Expectation Maximization–Based Learned AMP Network With CNN Deep Residual Network for Millimeter Wave Communication

Philip,

2024

Int J Communication

View full text Add to dashboard Cite

In millimeter wave (mmWave) multiple input and multiple output (MIMO) hybrid systems, estimating beamspace channels is complex due to the use of fewer RF chains compared with the number of transceiver antennas. Additionally, beamspace channels exhibit sparsity, making channel estimation a sparse signal recovery problem. This problem can be addressed using iterative algorithms such as orthogonal matching pursuit (OMP), approximate message passing (AMP), and learned AMP (LAMP) enabled by deep neural networks (DNNs). Two methods—GM‐LAMP and GM‐EM‐LAMP—have been proposed in the literature to improve channel estimation accuracy further. The GM‐LAMP algorithm employs a Gaussian mixture (GM)–based shrinkage function within the LAMP network to enhance estimation accuracy. The GM‐EM‐LAMP algorithm incorporates the expectation maximization (EM) algorithm to recover channel information from the beamspace channel vector. However, both methods result in noisy computed channel matrices. This article addresses this challenge by proposing a GM‐EM‐LAMP network integrated with a convolutional neural network deep residual network (CDRN). The proposed method enhances the contraction function and the DNN, modeling channel estimation as a denoising problem using an element‐wise subtraction structure. The spatial properties of the channel matrix are estimated using GM‐EM‐LAMP, and the outputs of GM‐EM‐LAMP are fed into the CDRN network. Compared with existing algorithms such as LS‐CDRN, OMP‐CDRN, AMP‐CDRN, LAMP‐CDRN, and GM‐LAMP‐CDRN, the proposed approach provides superior results in terms of normalized mean squared error (NMSE) and enhanced spectral gains.

show abstract

The Performance Analysis on Channel Estimation in Millimeter-Wave Communication and Their Challenges

Shoukath Ali,

Ahmad Khan,

Perarasi

et al. 2024

Next Generation Wireless Communication

View full text Add to dashboard Cite

Sparse Bayesian Learning Kalman Filter-based Channel Estimation for Hybrid Millimeter Wave MIMO Systems: A Frequency Domain Approach

Cited by 10 publications

References 32 publications

Learned-SBL-GAMP based hybrid precoders/combiners in millimeter wave massive MIMO systems

Learned-SBL-GAMP based hybrid precoders/combiners in millimeter wave massive MIMO systems

Gaussian Mixture—Expectation Maximization–Based Learned AMP Network With CNN Deep Residual Network for Millimeter Wave Communication

The Performance Analysis on Channel Estimation in Millimeter-Wave Communication and Their Challenges

Contact Info

Product

Resources

About