End-to-End Deep Learning in Wireless Communication Systems: A Tutorial Review
🤖 AI Summary
This work presents a systematic review of deep learning–based end-to-end physical layer design for wireless communications, addressing the limitations of traditional block-wise optimization approaches that struggle with nonlinearities, hardware impairments, and complex network environments. Central to this framework is an autoencoder architecture that enables joint optimization of modulation, encoding/decoding, and channel estimation within a unified neural network. The approach demonstrates superior performance across canonical scenarios—including point-to-point, multiple-access, and interference channels—effectively bridging the gap between theoretical models and practical deployment constraints. By integrating signal processing and communication theory with data-driven learning, this paradigm offers a promising technical pathway and outlines key research directions for next-generation wireless systems.
Application Category
📝 Abstract
The physical layer (PHY) in wireless communication systems has traditionally relied on model-based methods that are often optimized individually as independent blocks to perform tasks such as modulation, coding, and channel estimation. However, these approaches face challenges when it comes to capturing real-world nonlinearities, hardware imperfections, and increasing complexity in modern networks. This paper surveys advancements in applying deep learning (DL) for end-to-end PHY optimization by incorporating the autoencoder (AE) model as a powerful end-to-end DL framework to enable joint transmitter and receiver optimization and address challenges like dynamic channel conditions and scalability. We review cutting-edge DL models; their applications in PHY tasks such as modulation, error correction, and channel estimation; and their deployment in real-world scenarios, including point-to-point communication, multiple access, and interference channels. This work highlights the benefits of learning-based approaches over traditional methods, offering a comprehensive resource for researchers and engineers looking to innovate in next-generation wireless systems. Key insights and future directions are discussed to bridge the gap between theory and practical implementation.
Problem
Research questions and friction points this paper is trying to address.
wireless communication
physical layer
nonlinearities
hardware imperfections
end-to-end optimization
Innovation
Methods, ideas, or system contributions that make the work stand out.
end-to-end deep learning
autoencoder
physical layer optimization
wireless communication
joint transceiver design
🔎 Similar Papers
No similar papers found.
