Deep Denoising Neural Network Assisted Compressive Channel Estimation for mmWave Intelligent Reflecting Surfaces

Liu, Shicong; Gao, Zhen; Zhang, Jun; Renzo, Marco Di; Alouini, Mohamed‐Slim

doi:10.1109/tvt.2020.3005402

Cited by 274 publications

(138 citation statements)

References 16 publications

Supporting

Mentioning

138

Contrasting

Order By: Relevance

“…An alternative approach to mmWave channel estimation is to adopt the compressed sensing (CS), which can be leveraged to effectively estimate mmWave massive MIMO channels [14]- [16]. More recently, CS techniques combine with deep denoising neural network has been advocated for IRS-assisted mmWave channel estimation that substantiality reduce the pilot overhead [17]. These CS-based approaches exploit the the limited scattering characteristics of mmWave propagation to form a sparse channel recovery problem [18], [19].…”

Section: Introductionmentioning

confidence: 99%

“…In particular, as the development of urbanization, the line-of-sight (LoS) link is blocked by more and more high-rise buildings emerge in dense down town. On the other hand, the study in [15], [17], [24] adapts CS-based channel estimation to reliably estimate and feed back the CSI, which achieves accurate CSI acquisition. These prior works are restricted to conventional single objective design, which yield to the fixed solution path in the optimization process and leads to the suboptimal sparse solution by fixed regularization parameter.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Hybrid Evolutionary-Based Sparse Channel Estimation for IRS-Assisted mmWave MIMO Systems

Chen

Tang

Zhang

et al. 2022

IEEE Trans. Wireless Commun.

112

View full text Add to dashboard Cite

The intelligent reflecting surface (IRS)-assisted millimeter wave (mmWave) communication system has emerged as a promising technology for coverage extension and capacity enhancement. Prior works on IRS have mostly assumed perfect channel state information (CSI), which facilitates in deriving the upper-bound performance but is difficult to realize in practice due to passive elements of IRS without signal processing capabilities. In this paper, we propose a compressive channel estimation techniques for IRS-assisted mmWave multi-input and multi-output (MIMO) system. To reduce the training overhead, the inherent sparsity of mmWave channels is exploited. By utilizing the properties of Kronecker products, IRS-assisted mmWave channel is converted into a sparse signal recovery problem, which involves two competing cost function terms (measurement error and sparsity term). Existing sparse recovery algorithms solve the combined contradictory objectives function using a regularization parameter, which leads to a suboptimal solution. To address this concern, a hybrid multiobjective evolutionary paradigm is developed to solve the sparse recovery problem, which can overcome the difficulty in the choice of regularization parameter value. Simulation results show that under a wide range of simulation settings, the proposed method achieves competitive error performance compared to existing channel estimation methods.

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Hybrid Evolutionary-Based Sparse Channel Estimation for IRS-Assisted mmWave MIMO Systems

Chen

Tang

Zhang

et al. 2022

IEEE Trans. Wireless Commun.

112

View full text Add to dashboard Cite

show abstract

“…The sparsity of channels in a transformdomain is a crucial feature, which motivates the employment of compressive sensing approaches [30]. Recently, this feature has been exploited to CNN-based CE [31] and channel state information feedback [32].…”

Section: Introductionmentioning

confidence: 99%

Dual CNN-Based Channel Estimation for MIMO-OFDM Systems

Jiang

Wen

Jin

et al. 2021

IEEE Trans. Commun.

View full text Add to dashboard Cite

Recently, convolutional neural network (CNN)based channel estimation (CE) for massive multiple-input multiple-output communication systems has achieved remarkable success. However, complexity even needs to be reduced, and robustness can even be improved. Meanwhile, existing methods do not accurately explain which channel features help the denoising of CNNs. In this paper, we first compare the strengths and weaknesses of CNN-based CE in different domains. When complexity is limited, the channel sparsity in the angle-delay domain improves denoising and robustness whereas large noise power and pilot contamination are handled well in the spatialfrequency domain. Thus, we develop a novel network, called dual CNN, to exploit the advantages in the two domains. Furthermore, we introduce an extra neural network, called HyperNet, which learns to detect scenario changes from the same input as the dual CNN. HyperNet updates several parameters adaptively and combines the existing dual CNNs to improve robustness. Experimental results show improved estimation performance for the time-varying scenarios. To further exploit the correlation in the time domain, a recurrent neural network framework is developed, and training strategies are provided to ensure robustness to the changing of temporal correlation. This design improves channel estimation performance but its complexity is still low.

show abstract

“…At the time of writing, machine learning is attracting increasing attention in wireless communications [18][19][20][21]. In particular, by employing neural networks (NNs), nearoptimal low-complexity channel estimation and/or data detection can be achieved for different physical-layer communication schemes, relying either on a data-driven approach [22,23], where no mathematical model is required, or on a model-driven basis [24][25][26], which exploits the benefits of both well-established mathematical physical-layer communication models and of NNs.…”

Section: Introductionmentioning

confidence: 99%

Deep-Learning-Aided Joint Channel Estimation and Data Detection for Spatial Modulation

et al. 2020

View full text Add to dashboard Cite

Deep Denoising Neural Network Assisted Compressive Channel Estimation for mmWave Intelligent Reflecting Surfaces

Cited by 274 publications

References 16 publications

Hybrid Evolutionary-Based Sparse Channel Estimation for IRS-Assisted mmWave MIMO Systems

Hybrid Evolutionary-Based Sparse Channel Estimation for IRS-Assisted mmWave MIMO Systems

Dual CNN-Based Channel Estimation for MIMO-OFDM Systems

Deep-Learning-Aided Joint Channel Estimation and Data Detection for Spatial Modulation

Contact Info

Product

Resources

About