PAPR Reduction Scheme for Deep Learning-Based Communication Systems Using Autoencoders

Vahdat, Melika; Roshandeh, Koosha Pourtahmasi; Ardakani, Masoud; Jiang, Hai

doi:10.1109/vtc2020-spring48590.2020.9128513

Cited by 9 publications

(6 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Furthermore, ML techniques have also been used to lower out-of-band (OOB) emissions. A DL-based technique in terms of autoencoder has been employed for PAPR reduction [21]. A combination of extended SLM and autoencoder has also been proposed for reducing PAPR in DC-biased optical OFDM systems [22].…”

Section: For Papr Reductionmentioning

confidence: 99%

Future OFDM-based Communication Systems Towards 6G and Beyond: Machine Learning Approaches

Juwono

Reine²

2021

Green Intell. Syst. Appl.

View full text Add to dashboard Cite

The vision towards 6G and beyond communication systems demands higher rate transmission, massive amount of data processing, and low latency communication. Orthogonal Frequency Division Modulation (OFDM) has been adopted in the current 5G networks and has become one of the potential candidates for the future communication systems. Although OFDM offers many benefits including high spectrum efficiency and high robustness against the multipath fading channels, it has major challenges such as frequency offset and high Peak to Power Ratio (PAPR). In 5G communication network, there is a significant increase in the number of sensors and other low-power devices where users or devices may create large amount of connection and dynamic data processing. In order to deal with the increasingly complex communication network, Machine Learning (ML) has been increasingly utilised to create intelligent and more efficient communication network. This paper discusses challenges and the impacts of embedding ML in OFDM-based communication systems.

show abstract

Section: For Papr Reductionmentioning

confidence: 99%

Future OFDM-based Communication Systems Towards 6G and Beyond: Machine Learning Approaches

Juwono

Reine²

2021

Green Intell. Syst. Appl.

View full text Add to dashboard Cite

show abstract

“…Moreover, Jiang and others [9] proposed a sparsity‐learning‐based iterative algorithm for PAPR reduction to compensate for the distortion of clipped signals. Likewise, a deep neural network (DNN) architecture was provided by Vahdat to reduce the PAPR in autoencoder‐based communication systems, and others in [13]. Although these schemes displayed varying reduction levels in the PAPR, they showed insufficient improvement in either BER or computational complexity in addition to the requirement for a recovery process to be provided at the receiver in specific cases.…”

Section: Introductionmentioning

confidence: 99%

“…However, most of these techniques have shortcomings, such as poor system performance (bit error rate [BER]) and/or computational complexity. Well-known examples are distortionless schemes (e.g., SLM and PTS families) [2][3][4][5][6][7], clipping and filtering schemes [8,9], tone injection (TI) [10], active constellation extension (ACE) [11], interleaving [12], encoding family schemes [13], and artificial intelligent families [13][14][15][16][17][18]. Unfortunately, none of these solutions can guarantee the achievement of all standards, that is, acceptable levels of PAPR, BER performance, and computational complexity.…”

Section: Introductionmentioning

confidence: 99%

A conditionally applied neural network algorithm for PAPR reduction without the use of a recovery process

Eldukhri,

Al‐Rayif

2023

ETRI Journal

View full text Add to dashboard Cite

This study proposes a novel, conditionally applied neural network technique to reduce the overall peak‐to‐average power ratio (PAPR) of an orthogonal frequency division multiplexing (OFDM) system while maintaining an acceptable bit error rate (BER) level. The main purpose of the proposed scheme is to adjust only those subcarriers whose peaks exceed a given threshold. In this respect, the developed C‐ANN algorithm suppresses only the peaks of the targeted subcarriers by slightly shifting the locations of their corresponding frequency samples without affecting their phase orientations. In turn, this achieves a reasonable system performance by sustaining a tolerable BER. For practical reasons and to cover a wide range of application scenarios, the threshold for the subcarrier peaks was chosen to be proportional to the saturation level of the nonlinear power amplifier used to pass the generated OFDM blocks. Consequently, the optimal values of the factor controlling the peak threshold were obtained that satisfy both reasonable PAPR reduction and acceptable BER levels. Furthermore, the proposed system does not require a recovery process at the receiver, thus making the computational process less complex. The simulation results show that the proposed system model performed satisfactorily, attaining both low PAPR and BER for specific application settings using comparatively fewer computations.

show abstract

“…Consequently, performance is not guaranteed if the actual channel deviates from the training model. A modification to this method was proposed in [13], which replaced the two-variable loss function with a single loss function designed to decode transmissions. A scaled 'tanh' activation function was used at the output of the encoder to limit PAPR.…”

Section: Introductionmentioning

confidence: 99%

“…Residual learning has already shown significant success in image processing [15]. Different from [12][13][14], the proposed method makes no changes to the receiver, thus making it channel agnostic. Furthermore, the training process has been modified to account for OOBE as well as in-band distortion, while the clipper ensures a deterministic peak amplitude.…”

Section: Introductionmentioning

confidence: 99%

Mitigating Clipping Distortion in OFDM Using Deep Residual Learning

Omar

2021

ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

View full text Add to dashboard Cite

The high peak-to-average power ratio (PAPR) of orthogonal frequency division multiplexing (OFDM) transmissions is susceptible to non-linear distortion caused by power amplifier (PA) saturation. In this work, we propose a novel technique, using residual neural networks and soft clipping, to deterministically limit the peak amplitude of the signal, thus lowering its PAPR and circumventing PA distortion. We show that the proposed solution is capable of significantly reducing PAPR and in-band distortion, while obeying a spectral mask. Furthermore, we show that the neural network is able to generalize for a range of peak amplitudes, thus eliminating the need to re-train the network when the requirement changes.

show abstract

PAPR Reduction Scheme for Deep Learning-Based Communication Systems Using Autoencoders

Cited by 9 publications

References 10 publications

Future OFDM-based Communication Systems Towards 6G and Beyond: Machine Learning Approaches

Future OFDM-based Communication Systems Towards 6G and Beyond: Machine Learning Approaches

A conditionally applied neural network algorithm for PAPR reduction without the use of a recovery process

Mitigating Clipping Distortion in OFDM Using Deep Residual Learning

Contact Info

Product

Resources

About