Deep Learning in Wireless Communication Receivers: A Survey

Abstract

The design of wireless communication receivers to enhance signal processing in complex and dynamic environments is going through a transformation by leveraging deep neural networks (DNNs). Traditional wireless receivers depend on models and algorithms, which do not have the ability to learn from data. In contrast, deep learning-based receivers are more suitable for modern wireless communication systems because they can learn from data and adapt accordingly. This survey explores various deep learning architectures such as multilayer perceptrons (MLPs), convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and autoencoders, focusing on their application in the design of wireless receivers. Key modules of a receiver such as synchronization, channel estimation, equalization, space-time decoding, demodulation, decoding, interference cancellation, and modulation classification are discussed in the context of advanced wireless technologies like orthogonal frequency division multiplexing (OFDM), multiple input multiple output (MIMO), semantic communication, task-oriented communication, and next-generation (Next-G) networks. This survey fills a critical gap by providing a wireless receiver-focused deep learning roadmap, systematically mapping DNNs to each receiver stage, reviewing DL-enabled semantic and task-oriented reception, unifying state-of-the-art solutions for OFDM/MIMO, high-mobility links, and DL-enabled interference cancellation in a single reference. The survey not only emphasizes the potential of deep learning-based receivers in future wireless communication but also highlights different challenges of deep learning-based receivers, such as data availability, security and privacy concerns, model interpretability, computational complexity, and integration with legacy systems.

Topics & Concepts