Deep learning for wireless physical layer: Opportunities and challenges

By Tianqi Wang, Chao-Kai Wen, Hanqing Wang, F. Gao, Tao Jiang, Shi Jin. China Communications, 2017

572 citations recorded by the source corpus.

Machine learning (ML) has been widely applied to the upper layers of wireless communication systems for various purposes, such as deployment of cognitive radio and communication network. However, its application to the physical layer is hampered by sophisticated channel environments and limited learning ability of conventional ML algorithms. Deep learning (DL) has been recently applied for many fields, such as computer vision and natural language processing, given its expressive capacity and convenient optimization capability. The potential application of DL to the physical layer has also been increasingly recognized because of the new features for future communications, such as complex scenarios with unknown channel models, high speed and accurate processing requirements; these features challenge conventional communication theories. This paper presents a comprehensive overview of the emerging studies on DL-based physical layer processing, including leveraging DL to redesign a module of the conventional communication system (for modulation recognition, channel decoding, and detection) and replace the communication system with a radically new architecture based on an autoencoder. These DL-based methods show promising performance improvements but have certain limitations, such as lack of solid analytical tools and use of architectures that are specifically designed for communication and implementation research, thereby motivating future research in this field.

Subfields: Artificial Intelligence, Electrical and Electronic Engineering

View Paper: https://www.semanticscholar.org/paper/088592bc2ecfe04f0feab1a446402cd6578a0fdb

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Electrical and Electronic Engineering

Citations in the corpus

Application of Machine Learning in Wireless Networks: Key Techniques and Open Issues (2018, background): “A similar idea is presented in [30], where a broader area is surveyed including modulation recognition, channel decoding and signal detection.”
Machine Learning in IoT Security: Current Solutions and Future Challenges (2019, background): “and feature representation motivated by layered learning process in the human brain [99].”
Wireless Networks Design in the Era of Deep Learning: Model-Based, AI-Based, or Both? (2019, methodology): “Surveys on the use of ANNs to implement encoding/decoding operations as well as channel estimation tasks with limited side information have appeared in [184], [185].”
Machine Learning for Resource Management in Cellular and IoT Networks: Potentials, Current Solutions, and Open Challenges (2019, background): “DL learns features at multiple abstraction levels and allows a system to learn complex functions, and maps the input to the output directly from data [112].”
A Deep Learning Framework for Optimization of MISO Downlink Beamforming (2019, background): “Finally, [36, 37] provide an overview on the recent advances in DL-based physical layer communications and [38] suggests potential applications of DL to the physical layer.”
Deep Learning for Massive MIMO CSI Feedback (2017, methodology): “1For an overview of applying DL to the wireless physical layer, we refer the interested readers to [13].”
Deep Learning for Physical-Layer 5G Wireless Techniques: Opportunities, Challenges and Solutions (2019, background): “However, low-resolution analog-to-digital converters used in current frameworks cause unexpected nonlinear imperfections, which calls for rigorously robust processing methods with high computational complexity [12].”
Quantum Machine Learning for 6G Communication Networks: State-of-the-Art and Vision for the Future (2019, background): “Moreover, a survey on opportunities and challenges in deploying DL at the physical layer of wireless communication systems has been discussed in [100], where the scope of DNNs for channel estimation and channel encoding/decoding tasks has been thoroughly investigated.”
A Survey of Deep Learning and Its Applications: A New Paradigm to Machine Learning (2019, background): “Wang et al. [62] put forward a systematic survey of the upbringing studies based on the deep learning based physical layer processing, redesigning of a module for the communi-cational system with the auto encoder.”
Deep Learning Based Transmit Power Control in Underlaid Device-to-Device Communication (2019, background): “Recently, deep learning technology has begun to be applied in wireless communication systems [10], [12], [14]–[16], e.”
Future Intelligent and Secure Vehicular Network Toward 6G: Machine-Learning Approaches (2020, methodology): “For example, Daniels et al. [60] proposed a K-nearest neighbor (KNN)-based supervised learning strategy for adaptive OFDM configuration, including modulation, convolutional coding, and bit interleaving.”
Data-Driven Deep Learning for Automatic Modulation Recognition in Cognitive Radios (2019, background): “Due to state-of-the-art performance of deep learning in the physical layer [3]–[8], deep learning has been introduced gradually into CR for a range of tasks, most of which can be categorized as either classification, regression, or decision-making.”
Evolution of Non-Terrestrial Networks From 5G to 6G: A Survey (2021, background): “For further readings and insights about supervised learning we refer the readers to [186], [187], [188] and to [189] for deep learning and its applications in wireless communications.”
Deep Learning-Based CSI Feedback Approach for Time-Varying Massive MIMO Channels (2018, background): “Recently, deep learning (DL) methods has been successfully applied in wireless communications [5]–[7].”
Massive Access for 5G and Beyond (2020, background): “Currently, machine learning, especially deep learning, is being applied in wireless communications for resource allocation, signal processing, channel estimation, and transceiver design [197].”
Deep Learning-Based Channel Estimation for Beamspace mmWave Massive MIMO Systems (2018, background): “Deep learning has been recently applied to solve compressive image recovery [5] and wireless communications [7], [8].”