End-to-End Learning for OFDM: From Neural Receivers to Pilotless Communication

Aoudia, Fayçal Ait; Hoydis, Jakob

doi:10.1109/twc.2021.3101364

Cited by 44 publications

(19 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In addition to CP, pilot overhead needs to be considered in OFDM systems to increase the spectral efficiency. In [192], firstly, the number of pilot symbols is removed partially without a decrease in error performance. Secondly, by using an AEbased NN, pilots are completely removed along with a learned constellation or superimposed pilots.…”

Section: Gfdm-immentioning

confidence: 99%

Deep Learning-Aided 6G Wireless Networks: A Comprehensive Survey of Revolutionary PHY Architectures

Ozpoyraz¹,

Dogukan²,

Gevez³

et al. 2022

Preprint

View full text Add to dashboard Cite

Deep learning (DL) has proven its unprecedented success in diverse fields such as computer vision, natural language processing, and speech recognition by its strong representation ability and ease of computation. As we move forward to a thoroughly intelligent society with 6G wireless networks, new applications and use-cases have been emerging with stringent requirements for next-generation wireless communications. Therefore, recent studies have focused on the potential of DL approaches in satisfying these rigorous needs and overcoming the deficiencies of existing model-based techniques. The main objective of this article is to unveil the state-of-the-art advancements in the field of DL-based physical layer (PHY) methods to pave the way for fascinating applications of 6G. In particular, we have focused our attention on four promising PHY concepts foreseen to dominate next-generation communications, namely massive multiple-input multiple-output (MIMO) systems, sophisticated multi-carrier (MC) waveform designs, reconfigurable intelligent surface (RIS)-empowered communications, and PHY security. We examine up-to-date developments in DL-based techniques, provide comparisons with state-of-the-art methods, and introduce a comprehensive guide for future directions. We also present an overview of the underlying concepts of DL, along with the theoretical background of well-known DL techniques. Furthermore, this article provides programming examples for a number of DL techniques and the implementation of a DL-based MIMO by sharing user-friendly code snippets, which might be useful for interested readers.

show abstract

Section: Gfdm-immentioning

confidence: 99%

Deep Learning-Aided 6G Wireless Networks: A Comprehensive Survey of Revolutionary PHY Architectures

Ozpoyraz¹,

Dogukan²,

Gevez³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…The authors integrate the orthogonal approximate message passing algorithm with the signal detection NN. The authors in [6] propose end-to-end learning with the purpose of eliminating orthogonal pilots in OFDM symbols by jointly optimizing parts of the transmitter and the receiver.…”

Section: Related Workmentioning

confidence: 99%

“…Thus, any individual classical processing block could be swapped with its ML block counterpart in a way that is transparent to the rest of the receiver chain. This fully modular approach distinguishes our work from other recent work that use NN-based solutions for cyclic prefix free [4], DFT free [5] or pilotless communications [6] in OFDM systems.…”

Section: Introductionmentioning

confidence: 99%

Neural Network-based OFDM Receiver for Resource Constrained IoT Devices

Soltani¹,

Cheng²,

Belgiovine³

et al. 2022

Preprint

View full text Add to dashboard Cite

Orthogonal Frequency Division Multiplexing (OFDM)-based waveforms are used for communication links in many current and emerging Internet of Things (IoT) applications, including the latest WiFi standards. For such OFDM-based transceivers, many core physical layer functions related to channel estimation, demapping, and decoding are implemented for specific choices of channel types and modulation schemes, among others. To decouple hard-wired choices from the receiver chain and thereby enhance the flexibility of IoT deployment in many novel scenarios without changing the underlying hardware, we explore a novel, modular Machine Learning (ML)-based receiver chain design. Here, ML blocks replace the individual processing blocks of an OFDM receiver, and we specifically describe this swapping for the legacy channel estimation, symbol demapping, and decoding blocks with Neural Networks (NNs). A unique aspect of this modular design is providing flexible allocation of processing functions to the legacy or ML blocks, allowing them to interchangeably coexist. Furthermore, we study the implementation cost-benefits of the proposed NNs in resource-constrained IoT devices through pruning and quantization, as well as emulation of these compressed NNs within Field Programmable Gate Arrays (FPGAs). Our evaluations demonstrate that the proposed modular NN-based receiver improves bit error rate of the traditional non-ML receiver by averagely 61% and 10% for the simulated and over-the-air datasets, respectively. We further show complexity-performance tradeoffs by presenting computational complexity comparisons between the traditional algorithms and the proposed compressed NNs.

show abstract

“…Such schemes do not assume any prespecified modulation scheme or waveform, but instead learn everything from scratch. Such end-to-end learning has been shown to have potential to outperform traditional heuristic radio links, e.g., by learning a better constellation shape [19] or by learning to communicate under a nonlinear PA [20].…”

Section: State Of the Artmentioning

confidence: 99%

HybridDeepRx: Deep Learning Receiver for High-EVM Signals

Pihlajasalo

Korpi

Honkala

et al. 2021

2021 IEEE 32nd Annual International Symposium on Personal, Indoor and Mobile Radio Communications (PIMRC)

View full text Add to dashboard Cite

In this paper, we propose a machine learning (ML) based physical layer receiver solution for demodulating OFDM signals that are subject to a high level of nonlinear distortion. Specifically, a novel deep learning based convolutional neural network receiver is devised, containing layers in both timeand frequency domains, allowing to demodulate and decode the transmitted bits reliably despite the high error vector magnitude (EVM) in the transmit signal. Extensive set of numerical results is provided, in the context of 5G NR uplink incorporating also measured terminal power amplifier characteristics. The obtained results show that the proposed receiver system is able to clearly outperform classical linear receivers as well as existing ML receiver approaches, especially when the EVM is high in comparison with modulation order. The proposed ML receiver can thus facilitate pushing the terminal power amplifier (PA) systems deeper into saturation, and thereon improve the terminal power-efficiency, radiated power and network coverage.

show abstract

End-to-End Learning for OFDM: From Neural Receivers to Pilotless Communication

Cited by 44 publications

References 29 publications

Deep Learning-Aided 6G Wireless Networks: A Comprehensive Survey of Revolutionary PHY Architectures

Deep Learning-Aided 6G Wireless Networks: A Comprehensive Survey of Revolutionary PHY Architectures

Neural Network-based OFDM Receiver for Resource Constrained IoT Devices

HybridDeepRx: Deep Learning Receiver for High-EVM Signals

Contact Info

Product

Resources

About