Deep Learning for Wireless Communications

Erpek, Tugba; O’Shea, Timothy J.; Sagduyu, Yalin E.; Shi, Yi; Clancy, T. Charles

doi:10.1007/978-3-030-31764-5_9

Cited by 125 publications

(57 citation statements)

References 87 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Machine learning algorithms have lately shown a great prospective in treating complex optimization problems in the emerging wireless communications applications and settings [253]. For instance, there is a plethora of detection techniques for massive MIMO based on machine learning [254]- [256].…”

Section: Machine Learning Precodingmentioning

confidence: 99%

Overview of Precoding Techniques for Massive MIMO

et al. 2021

View full text Add to dashboard Cite

Massive multiple-input multiple-output (MIMO) is playing a crucial role in the fifth generation (5G) and beyond 5G (B5G) communication systems. Unfortunately, the complexity of massive MIMO systems is tremendously increased when a large number of antennas and radio frequency chains (RF) are utilized. Therefore, a plethora of research efforts has been conducted to find the optimal precoding algorithm with lowest complexity. The main aim of this paper is to provide insights on such precoding algorithms to a generalist of wireless communications. The added value of this paper is that the classification of massive MIMO precoding algorithms is provided with easily distinguishable classes of precoding solutions. This paper covers linear precoding algorithms starting with precoders based on approximate matrix inversion methods such as the truncated polynomial expansion (TPE), the Neumann series approximation (NSA), the Newton iteration (NI), and the Chebyshev iteration (CI) algorithms. The paper also presents the fixed-point iteration-based linear precoding algorithms such as the Gauss-Seidel (GS) algorithm, the successive over relaxation (SOR) algorithm, the conjugate gradient (CG) algorithm, and the Jacobi iteration (JI) algorithm. In addition, the paper reviews the direct matrix decomposition based linear precoding algorithms such as the QR decomposition and Cholesky decomposition (CD). The non-linear precoders are also presented which include the dirty-paper coding (DPC), Tomlinson-Harashima (TH), vector perturbation (VP), and lattice reduction aided (LR) algorithms. Due to the necessity to deal with a high consuming power by the base station (BS) with a large number of antennas in massive MIMO systems, a special subsection is included to describe the characteristics of the peak-to-average power ratio precoding (PAPR) algorithms such as the constant envelope (CE) algorithm, approximate message passing (AMP), and quantized precoding (QP) algorithms. This paper also reviews the machine learning role in precoding techniques. Although many precoding techniques are essentially proposed for a small-scale MIMO, they have been exploited in massive MIMO networks. Therefore, this paper presents the application of small-scale MIMO precoding techniques for massive MIMO. This paper demonstrates the precoding schemes in promising multiple antenna technologies such as the cell-free massive MIMO (CF-M-MIMO), beamspace massive MIMO, and intelligent reflecting surfaces (IRSs). In-depth discussion on the pros and cons, performance-complexity profile, and implementation solidity is provided. This paper also provides a discussion on the channel estimation and energy efficiency. This paper also presents potential future directions in massive MIMO precoding algorithms.

show abstract

Section: Machine Learning Precodingmentioning

confidence: 99%

Overview of Precoding Techniques for Massive MIMO

et al. 2021

View full text Add to dashboard Cite

show abstract

“…This discovery constituted a major breakthrough in the design of communication systems and has been widely employed in many research efforts. A chapter in a recent book [14] described the benefits and the use of end-to-end learning for channel estimation, signal identification, and wireless security. Qin et al [15] demonstrated the applications of DL to the optimization of individual signal processing blocks in the physical layer (e.g., signal compression and detection) and also end-to-end design.…”

Section: B State-of-the-artmentioning

confidence: 99%

“…Existing surveys (e.g., [21], [22], [25], [28]) are limited to the scope of mobile networking and communications. Furthermore, most existing studies focus on certain AI techniques and their applications to wireless research such as channel encoding and decoding [8], [36], unfolding DL for MIMO systems [17], DL for wireless networks [13], [15], [16], and tracking and localization [37]. In contrast, our aim was to provide a comprehensive survey of AI applications for various aspects of wireless physical signal processing.…”

Section: Contributions and Organization Of This Papermentioning

confidence: 99%

“…[13] DL for modulation, channel coding, detection, and end-to-end learning. [14] End-to-end learning for wireless networks: channel estimation, signal identification, and wireless security. [15] Applications of DL for block optimization and end-to-end design.…”

Section: Contributions and Organization Of This Papermentioning

confidence: 99%

“…Generally, AI has great potential to provide effective end-to-end solutions. Motivated by recent seminal work [8], many studies have been dedicated to improving wireless systems, e.g., modulation identification and channel estimation for spectrum situation awareness and wireless security [36]. However, many challenges remain for end-to-end learning when various features and new requirements are taken into consideration.…”

Section: A End-to-end Learningmentioning

confidence: 99%

See 2 more Smart Citations

Intelligent Radio Signal Processing: A Survey

et al. 2021

View full text Add to dashboard Cite

Intelligent signal processing for wireless communications is a vital task in modern wireless systems, but it faces new challenges because of network heterogeneity, diverse service requirements, a massive number of connections, and various radio characteristics. Owing to recent advancements in big data and computing technologies, artificial intelligence (AI) has become a useful tool for radio signal processing and has enabled the realization of intelligent radio signal processing. This survey covers four intelligent signal processing topics for the wireless physical layer, including modulation classification, signal detection, beamforming, and channel estimation. In particular, each theme is presented in a dedicated section, starting with the most fundamental principles, followed by a review of up-to-date studies and a summary. To provide the necessary background, we first present a brief overview of AI techniques such as machine learning, deep learning, and federated learning. Finally, we highlight a number of research challenges and future directions in the area of intelligent radio signal processing. We expect this survey to be a good source of information for anyone interested in intelligent radio signal processing, and the perspectives we provide therein will stimulate many more novel ideas and contributions in the future.

show abstract

Synchronization techniques for underwater acoustic communications

Babu

Ameer

Koilpillai

2023

Int J Communication

View full text Add to dashboard Cite

SummaryUnderwater acoustic channel is a challenging medium for communication due to the presence of significant multipath, high noise, frequency‐dependent propagation loss, and high and non‐uniform Doppler spread. Doppler shift is non‐negligible in underwater communication due to the low velocity of underwater signals. Synchronization and Doppler estimation are important requirements for achieving good performance in this channel. Synchronization algorithms that give good performance in radio communication do not work well in underwater communication. Hence, this area has received a lot of attention from researchers. This paper surveys important works in the area. The techniques proposed in the literature for frame synchronization, frequency and phase synchronization, and timing synchronization in single carrier communications are reviewed here. The synchronization techniques proposed for OFDM, MIMO OFDM, and spread spectrum communication are also surveyed. Doppler estimation methods proposed in the literature are also reviewed. It is found that most of the recent works in underwater acoustic communication focus on OFDM synchronization. Deep learning‐based methods proposed in the literature are also reviewed. Key open problems and areas that require future research attention in the field of synchronization and Doppler estimation in underwater communications are highlighted in this paper. The area needing most attention of underwater communication researchers was found to be MIMO OFDM due to the difficulty in synchronization in such systems while used in underwater communication. Reducing the computational complexity of the algorithms used is also important for future work. Schemes that work with Doppler due to relative velocity over 10 m/s also need to be developed.

show abstract

Deep Learning for Wireless Communications

Cited by 125 publications

References 87 publications

Overview of Precoding Techniques for Massive MIMO

Overview of Precoding Techniques for Massive MIMO

Intelligent Radio Signal Processing: A Survey

Synchronization techniques for underwater acoustic communications

Contact Info

Product

Resources

About