Model-Driven Deep Learning for Physical Layer Communications

Intelligent communication is gradually becoming a mainstream direction. As a major branch of machine learning, deep learning (DL) has been applied in physical layer communications and has demonstrated an impressive performance improvement in recent years. However, most existing works related to DL focus on data-driven approaches, which consider the communication system as a black box and train it by using a huge volume of data. Training a network requires sufficient computing resources and extensive time, both of which are rarely found in communication devices. By contrast, model-driven DL approaches combine communication domain knowledge with DL to reduce the demand for computing resources and training time. This article discusses the recent advancements in model-driven DL approaches in physical layer communications, including transmission schemes, receiver design, and channel information recovery. Several open issues for future research are also highlighted.

Introduction

Modern wireless communication systems have developed from the first to the fourth generation and have propelled to the fifth generation (5G) to provide advanced wireless services, such as virtual reality, autonomous driving, and Internet of Things (IoT). Enhanced mobile broadband, massive machine-type communications, and ultra-reliable and low-latency communications are the three main scenarios for 5G wireless networks. They require communication systems to have the ability to handle a large amount of wireless data, recognize and dynamically adapt to complex environments, and satisfy the requirements for high speed and accurate processing. Therefore, future wireless communication systems must be highly intelligent.