The Extended SLM Combined Autoencoder of the PAPR Reduction Scheme in DCO-OFDM Systems

End-to-end learning in optical communication systems is a promising technique to solve difficult communication problems, especially for peak to average power ratio (PAPR) reduction in orthogonal frequency division multiplexing (OFDM) systems. The less complex, highly adaptive hardware and advantages...

Full description

Bibliographic Details
Main Authors: Lili Hao, Dongyi Wang, Yang Tao, Wenyong Cheng, Jing Li, Zehan Liu
Format: Article
Language:English
Published: MDPI AG 2019-02-01
Series:Applied Sciences
Subjects:
Online Access:https://www.mdpi.com/2076-3417/9/5/852
id doaj-a03236082c6040ea9c544a3c83052e00
record_format Article
spelling doaj-a03236082c6040ea9c544a3c83052e002020-11-24T21:35:54ZengMDPI AGApplied Sciences2076-34172019-02-019585210.3390/app9050852app9050852The Extended SLM Combined Autoencoder of the PAPR Reduction Scheme in DCO-OFDM SystemsLili Hao0Dongyi Wang1Yang Tao2Wenyong Cheng3Jing Li4Zehan Liu5School of Information and Electrical Engineering, Shandong Jianzhu University, Jinan 250101, ChinaBio-Imaging and Machine Vision Lab, Fischell Department of Bioengineering, University of Maryland, College Park, MA 20740, USABio-Imaging and Machine Vision Lab, Fischell Department of Bioengineering, University of Maryland, College Park, MA 20740, USAAdvanced Research Center for Optics, Shandong University, Jinan 250100, ChinaCETC key laboratory of aerospace information applications, Shijiazhuang 050081, ChinaSchool of Information and Electrical Engineering, Shandong Jianzhu University, Jinan 250101, ChinaEnd-to-end learning in optical communication systems is a promising technique to solve difficult communication problems, especially for peak to average power ratio (PAPR) reduction in orthogonal frequency division multiplexing (OFDM) systems. The less complex, highly adaptive hardware and advantages in the analysis of unknown or complex channels make deep learning a valid tool to improve system performance. In this paper, we propose an autoencoder network combined with extended selected mapping methods (ESLM-AE) to reduce the PAPR for the DC-biased optical OFDM system and to minimize the bit error rate (BER). The constellation mapping/de-mapping of the transmitted symbols and the phase factor of each subcarrier are acquired and optimized adaptively by training the autoencoder with a combined loss function. In the loss function, both the PAPR and BER performance are taken into account. The simulation results show that a significant PAPR reduction of more than 10 dB has been achieved by using the ESLM-AE scheme in terms of the complementary cumulative distribution function. Furthermore, the proposed scheme exhibits better BER performance compared to the standard PAPR reduction methods.https://www.mdpi.com/2076-3417/9/5/852orthogonal frequency division multiplexingautoencoderend-to-end learningpeak-to-average power ratio
collection DOAJ
language English
format Article
sources DOAJ
author Lili Hao
Dongyi Wang
Yang Tao
Wenyong Cheng
Jing Li
Zehan Liu
spellingShingle Lili Hao
Dongyi Wang
Yang Tao
Wenyong Cheng
Jing Li
Zehan Liu
The Extended SLM Combined Autoencoder of the PAPR Reduction Scheme in DCO-OFDM Systems
Applied Sciences
orthogonal frequency division multiplexing
autoencoder
end-to-end learning
peak-to-average power ratio
author_facet Lili Hao
Dongyi Wang
Yang Tao
Wenyong Cheng
Jing Li
Zehan Liu
author_sort Lili Hao
title The Extended SLM Combined Autoencoder of the PAPR Reduction Scheme in DCO-OFDM Systems
title_short The Extended SLM Combined Autoencoder of the PAPR Reduction Scheme in DCO-OFDM Systems
title_full The Extended SLM Combined Autoencoder of the PAPR Reduction Scheme in DCO-OFDM Systems
title_fullStr The Extended SLM Combined Autoencoder of the PAPR Reduction Scheme in DCO-OFDM Systems
title_full_unstemmed The Extended SLM Combined Autoencoder of the PAPR Reduction Scheme in DCO-OFDM Systems
title_sort extended slm combined autoencoder of the papr reduction scheme in dco-ofdm systems
publisher MDPI AG
series Applied Sciences
issn 2076-3417
publishDate 2019-02-01
description End-to-end learning in optical communication systems is a promising technique to solve difficult communication problems, especially for peak to average power ratio (PAPR) reduction in orthogonal frequency division multiplexing (OFDM) systems. The less complex, highly adaptive hardware and advantages in the analysis of unknown or complex channels make deep learning a valid tool to improve system performance. In this paper, we propose an autoencoder network combined with extended selected mapping methods (ESLM-AE) to reduce the PAPR for the DC-biased optical OFDM system and to minimize the bit error rate (BER). The constellation mapping/de-mapping of the transmitted symbols and the phase factor of each subcarrier are acquired and optimized adaptively by training the autoencoder with a combined loss function. In the loss function, both the PAPR and BER performance are taken into account. The simulation results show that a significant PAPR reduction of more than 10 dB has been achieved by using the ESLM-AE scheme in terms of the complementary cumulative distribution function. Furthermore, the proposed scheme exhibits better BER performance compared to the standard PAPR reduction methods.
topic orthogonal frequency division multiplexing
autoencoder
end-to-end learning
peak-to-average power ratio
url https://www.mdpi.com/2076-3417/9/5/852
work_keys_str_mv AT lilihao theextendedslmcombinedautoencoderofthepaprreductionschemeindcoofdmsystems
AT dongyiwang theextendedslmcombinedautoencoderofthepaprreductionschemeindcoofdmsystems
AT yangtao theextendedslmcombinedautoencoderofthepaprreductionschemeindcoofdmsystems
AT wenyongcheng theextendedslmcombinedautoencoderofthepaprreductionschemeindcoofdmsystems
AT jingli theextendedslmcombinedautoencoderofthepaprreductionschemeindcoofdmsystems
AT zehanliu theextendedslmcombinedautoencoderofthepaprreductionschemeindcoofdmsystems
AT lilihao extendedslmcombinedautoencoderofthepaprreductionschemeindcoofdmsystems
AT dongyiwang extendedslmcombinedautoencoderofthepaprreductionschemeindcoofdmsystems
AT yangtao extendedslmcombinedautoencoderofthepaprreductionschemeindcoofdmsystems
AT wenyongcheng extendedslmcombinedautoencoderofthepaprreductionschemeindcoofdmsystems
AT jingli extendedslmcombinedautoencoderofthepaprreductionschemeindcoofdmsystems
AT zehanliu extendedslmcombinedautoencoderofthepaprreductionschemeindcoofdmsystems
_version_ 1725943546106609664