Low PAPR Waveform Design for OFDM Systems Based on Convolutional Autoencoder

Huleihel, Yara; Ben-Dror, Eilam; Permuter, Haim H.

doi:10.1109/ants50601.2020.9342801

Cited by 10 publications

(4 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this section, the radar and communication performance of NN‐RCI with respect to PAPR, BER, and the root mean square error (RMSE) of the target range and velocity estimation are provided. We compare the performance of NN‐RCI with that of the clipping method [10], CNN [27], and FC network [25].…”

Section: Simulation Resultsmentioning

confidence: 99%

See 1 more Smart Citation

Radar and communication integrated systems design based on deep neural networks

Liu

Cao

Mao

et al. 2023

IET Radar Sonar & Navi

View full text Add to dashboard Cite

Due to the spectrum congestion in the future 6G networks and the dramatic increasing requirement for the equipment that can detect and communicate simultaneously, the design of bi‐static radar and communication integrated (RCI) system is receiving more and more attention. Orthogonal frequency division multiplexing (OFDM) is a commonly used waveform in bi‐static RCI system. There are two gaps in current research that need to be filled. First, high peak‐to‐average ratio (PAPR) of OFDM signal is less considered in the conventional bi‐static RCI system due to the difficulty in recovering in the receiver. Second, the target echo estimation depends on the reconstruction of the direct‐path communication (DPC) signal. To overcome these limitations, we firstly propose a deep learning (DL)‐based transceiver design for the bi‐static RCI systems. Specifically, we design a neural network (NN)‐based waveform designer (WDNN) to reduce the PAPR of the transmit waveform, an NN‐based signal separator (SSN) to directly separate the target echo and the DPC signal, and an NN‐based symbol recovery (SRN) to demodulate the symbols. By using the training data and channel realisations, these three networks are jointly trained offline to minimise the PAPR of the transmit waveform, the separation error of the target echo and DPC signals, and the bit error rate. Then, in the online deployment phase, the trained WDNN is used to modify the transmitted waveform, and the trained SSN and SRN are placed at the receiver to separate signal and demodulate symbol. Simulation results show that compared to the conventional method, the proposed scheme not only reduces the PAPR but also improves the estimation of target parameters and communication symbol.

show abstract

Section: Simulation Resultsmentioning

confidence: 99%

“…For example, the authors in Ref. [25,27] use deep learning to design the symbol on each subcarrier to minimise the PAPR and bit error rate (BER) of the OFDM system. the authors in Ref.…”

Section: Introductionmentioning

confidence: 99%

Radar and communication integrated systems design based on deep neural networks

Liu

Cao

Mao

et al. 2023

IET Radar Sonar & Navi

View full text Add to dashboard Cite

show abstract

“…In [29], [30] the authors present an AE solution for PAPR reduction, while minimizing the BER degradation. In [31] a CAE was suggested for the implementation of an end-to-end SISO − OFDM communication network that simultaneously reduces the PAPR and reconstructs the transmitted symbols, while keeping acceptable spectral requirements. Another learning-based approach, which considers the reduction of the PAPR and ACPR together with the maximization of the achievable information rate for a single-carrier waveform above multipath channels, was proposed in [32].…”

Section: Deep-learning-based Schemes (Data Driven) For Papr Reductionmentioning

confidence: 99%

Low PAPR MIMO-OFDM Design Based on Convolutional Autoencoder

Huleihel¹,

Permuter²

2023

Preprint

View full text Add to dashboard Cite

An enhanced framework for peak-to-average power ratio (PAPR) reduction and waveform design for Multiple-Input-Multiple-Output (MIMO) orthogonal frequency-division multiplexing (OFDM) systems, based on a convolutional-autoencoder (CAE) architecture, is presented. The end-to-end learning-based autoencoder (AE) for communication networks represents the network by an encoder and decoder, where in between, the learned latent representation goes through a physical communication channel.We introduce a joint learning scheme based on projected gradient descent iteration to optimize the spectral mask behavior and MIMO detection under the influence of a non-linear high power amplifier (HPA) and a multipath fading channel. The offered efficient implementation novel waveform design technique utilizes only a single PAPR reduction block for all antennas. It is throughput-lossless, as no side information is required at the decoder. Performance is analyzed by examining the bit error rate (BER), the PAPR, and the spectral response and compared with classical PAPR reduction MIMO detector methods on 5G simulated data. The suggested system exhibits competitive performance when considering all optimization criteria simultaneously. We apply gradual loss learning for multi-objective optimization and show empirically that a single trained model covers the tasks of PAPR reduction, spectrum design, and MIMO detection together over a wide range of SNR levels.

show abstract

“…On the other hand, considerable out-ofband (OOB) emissions are known to be produced by OFDM system. As consequence, there has been a strong drive among physical layer scientists to investigate next level OFDM, as the future wireless networks will experience higher traffic volumes and minimum interference abidance [2][3][4]. In addition, filter-bank-multicarrier that deals with subcarrier level filtering, there are also universal-filtered multi-carrier and filtered-OFDM (f-OFDM) which offer sub-band level filtering, are popular candidates for filtered waveforms [5][6][7].…”

Section: Introductionmentioning

confidence: 99%

DFT-Spread WR-OCDM Communication System for the Reductions of OOB and PAPR

Rahman,

Ryu

2023

Preprint

View full text Add to dashboard Cite

Orthogonal chirp division multiplexing (OCDM) system has been considered as one candidate for the nextgeneration 6G cellular system that will support many new services and applications but will suffer from the sub-THz frequency band. It is anticipated that this will significantly harm the waveform orthogonality of conventional systems and lead to obnoxious intercarrier interference (ICI) and a very high propagation loss on information signals by introducing peak-to-average power ratio (PAPR). As a result, PAPR reduction is the most important aspect of 6G wireless communication system than 4G long-term evolution (LTE), 5G new radio (NR) schemes because it will use the Sub-THz frequency band which has a very high tendency toward propagation loss component. Therefore, spread spectrum technology termed as orthogonal chirp division multiplexing (OCDM) takes into account for the orthogonality of cyclically shifted quadratic chirp signals in order to increase spectral efficiency and reducing PAPR. The OCDM system, however, emits considerable out-of-band (OOB) power. To solve this problem, we suggest a new discrete Fourier transform (DFT)Spread Windowing and Restructuring (WR)-OCDM (DFT-Spread WR-OCDM) method for a suitably acceptable PAPR and OOB power emission reduction. In the system, the OOB power emissions are successfully reduced at the transmitter using time-domain windowing, and relatively shorter in window length is sufficient to satisfy the standard spectral mask. Comparing the proposed scheme to previous OFDM and OCDM systems, simulation findings show that this technique greatly reduces PAPR by about 2 dB and OOB power emission approximately by 64 dB and 70 dB. Additionally, we examine the bit error ratio (BER) performance using AWGN channel. This DFT-Spread WROCDM scheme performs almost similar results as compared to the conventional OFDM, OCDM, and WR-OCDM systems.

show abstract

Low PAPR Waveform Design for OFDM Systems Based on Convolutional Autoencoder

Cited by 10 publications

References 24 publications

Radar and communication integrated systems design based on deep neural networks

Radar and communication integrated systems design based on deep neural networks

Low PAPR MIMO-OFDM Design Based on Convolutional Autoencoder

DFT-Spread WR-OCDM Communication System for the Reductions of OOB and PAPR

Contact Info

Product

Resources

About