A Review of the State of the Art and Future Challenges of Deep Learning-Based Beamforming

Kassir, Haya Al; Zaharis, Zaharias D.; Lazaridis, Pavlos I.; Kantartzis, Nikolaos V.; Yioultsis, Traianos V.; Xenos, Thomas D.

doi:10.1109/access.2022.3195299

Cited by 39 publications

(17 citation statements)

References 117 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The potential of applying advanced optimization algorithms, such as Artificial Neural Networks (ANNs), is discussed in Supplementary Note 13 . Feedback sensing and control are essential components of adaptive wireless communication systems 55 , such as beamforming antennas 56 and cognitive radio systems 57 , facilitating optimal decision-making processes. They are integrated with our FPRFS for self-adaptive applications.…”

Section: Resultsmentioning

confidence: 99%

A multifunctional smart field-programmable radio frequency surface

Li,

Yu,

Liu

et al. 2024

Nat Commun

View full text Add to dashboard Cite

Antennas that can operate across multiple communication standards have remained a challenge. To address these limitations, we propose a Field-Programmable Radio Frequency Surface (FPRFS), which is based on manipulating current flow on its surface to achieve desirable RF characteristics. In this work, we demonstrate that substantial enhancements in radiation efficiency can be achieved while preserving the high reconfigurability of antenna structures implemented on the FPRFS. This is accomplished by utilizing an asymmetric excitation, directing the excitation to the low-loss contiguous surface, and dynamically manipulating the imaged return current on a segmented ground plane by switches. This important insight allows for adaptable antenna performance that weakly depends on the number of RF switches or their loss. We experimentally validate that FPRFS antennas can achieve efficiencies comparable to traditionally implemented antenna counterparts. This permits the FPRFS to be effectively utilized as a productive antenna and impedance-matching network with real-time reconfigurability.

show abstract

Section: Resultsmentioning

confidence: 99%

A multifunctional smart field-programmable radio frequency surface

Li,

Yu,

Liu

et al. 2024

Nat Commun

View full text Add to dashboard Cite

show abstract

“…It was also reported that fully distributed reinforcement learning (RL) estimates the uplink beamforming matrix by dividing the beamforming computations among distributed access points without significant accuracy deterioration [130]. We refer the reader to [131] for a comprehensive review of ML-based beamforming methods.…”

Section: Beamformingmentioning

confidence: 99%

Achievable Rate of Near-Field Communications Based on Physically Consistent Models

Akrout

Shyianov

Bellili

et al. 2023

IEEE Trans. Wireless Commun.

View full text Add to dashboard Cite

Data-driven machine learning (ML) is promoted as one potential technology to be used in next-generations wireless systems. This led to a large body of research work that applies ML techniques to solve problems in different layers of the wireless transmission link. However, most of these applications rely on supervised learning which assumes that the source (training) and target (test) data are independent and identically distributed (i.i.d). This assumption is often violated in the real world due to domain or distribution shifts between the source and the target data. Thus, it is important to ensure that these algorithms generalize to out-of-distribution (OOD) data. In this context, domain generalization (DG) tackles the OODrelated issues by learning models on different and distinct source domains/datasets with generalization capabilities to unseen new domains without additional finetuning. Motivated by the importance of DG requirements for wireless applications, we present a comprehensive overview of the recent developments in DG and the different sources of domain shift. We also summarize the existing DG methods and review their applications in selected wireless communication problems, and conclude with insights and open questions.

show abstract

“…The article [62] provides a comprehensive and detailed analysis of the recent state-ofthe-art AI applications in beamforming. First, the paper briefly overviews beamforming techniques and Direction of Arrival (DOA) estimation methods.…”

Section: Related Workmentioning

confidence: 99%

A Literature Survey on AI-Aided Beamforming and Beam Management for 5G and 6G Systems

Brilhante¹,

Manjares²,

Moreira³

et al. 2023

Preprint

View full text Add to dashboard Cite

The performance of modern wireless communication systems is highly dependent on the adoption of multiple antennas and the associated signal processing. In 5G and 6G networks, beamforming and beam management become challenging tasks due to aspects such as user mobility, increased number of antennas, and the adoption of higher frequencies. Artificial intelligence, and more specifically, machine learning, are efficient tools to reduce the complexity involved in generating beams and the overhead associated with beam management without sacrificing system performance. Therefore, AI-aided beamforming and beam management have received a lot of attention recently. This article presents a complete survey on this topic, emphasizing open problems and promising directions. The discussion includes architectural and signal processing aspects of modern beamforming and beam management. The article presents communication problems and respective solutions using centralized/decentralized, supervised/unsupervised, semi-supervised, active, federated, and reinforcement learning.

show abstract

A Review of the State of the Art and Future Challenges of Deep Learning-Based Beamforming

Cited by 39 publications

References 117 publications

A multifunctional smart field-programmable radio frequency surface

A multifunctional smart field-programmable radio frequency surface

Achievable Rate of Near-Field Communications Based on Physically Consistent Models

A Literature Survey on AI-Aided Beamforming and Beam Management for 5G and 6G Systems

Contact Info

Product

Resources

About