Deep Learning Design for Joint Antenna Selection and Hybrid Beamforming in Massive MIMO

Elbir, Ahmet M.; Mishra, Kumar Vijay

doi:10.1109/apusncursinrsm.2019.8888753

Cited by 20 publications

(12 citation statements)

References 48 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Through simulations it is established that the proposed method outperforms in terms of bit error rate compared to the existing traditional methods. [34] details beam allocation problem for massive MIMO sysem using deep neural networks.Beam selection and switching is performed using machine learning algorithms. Beams are produced by Butler metod to achieve large gain.…”

Section: Methodology Use Of Deep Learning In Beamforming In Mimomentioning

confidence: 99%

See 1 more Smart Citation

Marginal Deep Architectures Based Massive MIMO Beam Forming and Predictions

Venkatesan¹,

Kulkarni²,

Menon³

2020

HELIX

View full text Add to dashboard Cite

The increasing demands in 5G technology is fulfilled by MIMO systems which employ hundreds of antennas to serve the broadband terminals. Deep learning algorithms are powerful machine learning algorithms capable of advanced learning and predictions. Deep learning is largely employed in MIMO. This paper explores the usage of deep learning architectures in beam forming and predictions in MIMO. Specifically, an improvised version of deep learning is the marginal deep architecture. This paper also briefs about the usage of marginal deep architecture based methods for beam forming and predictions. Such proposed models will greatly improve the efficiency and capability of beam forming in MIMO resulting in improved 5G services.

show abstract

Section: Methodology Use Of Deep Learning In Beamforming In Mimomentioning

confidence: 99%

“…The performance is evaluated under different conditions. Hybrid beam forming for MIMO system is looked into under jamming environment [19].The proposed method has ability to reduce the covariance matrix and hence better interference mitigation. Simulations have been performed to confirm the effectiveness of the proposed method.…”

Section: Beamforming In Mimomentioning

confidence: 99%

Marginal Deep Architectures Based Massive MIMO Beam Forming and Predictions

Venkatesan¹,

Kulkarni²,

Menon³

2020

HELIX

View full text Add to dashboard Cite

show abstract

“…• Deep learning based hybrid beamforming algorithms: Recently, many studies exploited the machine learning algorithms to solve many traditional communication problems, such as implementing autoencoders at both the transmitter and receiver, signal representation prediction, modulation classification, and channel estimation [137], [138]. Additionally, there are also some studies that manipulated the problem for HBF for simple scenarios [139]- [141].…”

Section: Open Research Issuesmentioning

confidence: 99%

Taxonomy and Performance Evaluation of Hybrid Beamforming for 5G and Beyond Systems

Rihan

Soliman

et al. 2020

IEEE Access

View full text Add to dashboard Cite

Increasing demand for higher data-rate wireless connectivity with lower latency is fueling the explorations of millimeter-wave (mmWave) spectrum and massive MIMO communications. Both technologies are recognized as the key enablers of 5G and beyond 5G (B5G) networks. Hybrid beamforming is one of the most promising energy and cost-effective approaches to realize mmWave massive MIMO communications with lower complexity and smaller training overhead. With the motivation of giving more insights and in-deep technical recommendations to B5G network designers regarding hybrid beamforming, we present a hybrid beamforming taxonomy in terms of channel state information (CSI) availability, frequency bandwidth, architecture complexity, analog beamformer components, number of users, connectivity to RF chains, and the digital and analog beamforming design. Furthermore, we provide a comprehensive survey on the state-of-the-art use-cases for each classification followed by identification of the future challenges and open research issues. INDEX TERMS Hybrid beamforming (HBF), energy efficiency (EE), millimeter wave (mmWave), hardware complexity, massive-MIMO, analog beamforming (ABF), and digital beamforming (DBF).

show abstract

“…Specifically, we design a convolutional neural network (CNN) to achieve both tasks sequentially. The element selection problem is cast as a classification problem [38]. A similar DL approach was adopted for radar antenna arrays recently in [39].…”

Section: Introductionmentioning

confidence: 99%

“…While quantized-CNN structures are recently studied for image classification purposes, ours is the first work that examines quantized-CNNs for communications. Preliminary results of our work appeared in [38] and [42]; while a basic formulation suggested in [38] solved the joint problem for a specific hybrid beamforming scheme, [42] proposed a quantized-CNN approach for the same scheme but did not include antenna selection.…”

Section: Introductionmentioning

confidence: 99%

Joint Antenna Selection and Hybrid Beamformer Design Using Unquantized and Quantized Deep Learning Networks

Elbir

Mishra

2020

IEEE Trans. Wireless Commun.

Self Cite

146

116

View full text Add to dashboard Cite

In millimeter wave communications, multiple-inputmultiple-output (MIMO) systems use large antenna arrays to achieve high gain and spectral efficiency. These massive MIMO systems employ hybrid beamformers to reduce power consumption associated with fully digital beamforming in large arrays. Further savings in cost and power is possible through use of subarrays. Unlike prior works which resort to large latency methods such as optimization and greedy search for subarray selection, we propose a deep-learning-based approach in order to overcome the complexity issue without causing significant performance loss. We formulate antenna selection and hybrid beamformer design as a classification/prediction problem for convolutional neural networks (CNNs). For antenna selection, the CNN accepts the channel matrix as input and outputs a subarray with an optimal spectral efficiency. The resultant subarray channel matrix is then again fed to a CNN to obtain analog and baseband beamformers. We train the CNNs with several noisy channel matrices that have different channel statistics in order to achieve a robust performance at the network output. Numerical experiments show that our CNN framework provides an order better spectral efficiency and is 10 times faster than the conventional techniques. Further investigations with quantized-CNNs show that the proposed network, saved in no more than 5 bits, is also suited for digital mobile devices.Index Terms-Antenna selection, CNN, deep learning, hybrid beamforming, massive MIMO.A. M. E. is with the

show abstract

Deep Learning Design for Joint Antenna Selection and Hybrid Beamforming in Massive MIMO

Cited by 20 publications

References 48 publications

Marginal Deep Architectures Based Massive MIMO Beam Forming and Predictions

Marginal Deep Architectures Based Massive MIMO Beam Forming and Predictions

Taxonomy and Performance Evaluation of Hybrid Beamforming for 5G and Beyond Systems

Joint Antenna Selection and Hybrid Beamformer Design Using Unquantized and Quantized Deep Learning Networks

Contact Info

Product

Resources

About