Deep learning based asymmetrical autoencoder for PAPR reduction of CP-OFDM systems

Adoption of Orthogonal Frequency Division Multiplexing (OFDM) in 5th Generation New Radio (5G NR) as a multicarrier modulation technique allows high data rate transmission with lower complexity. However, problem such as peak to average power ratio (PAPR) has decreased the transmitter efficiency. Rec...

Full description

Bibliographic Details
Published in:ENGINEERING SCIENCE AND TECHNOLOGY-AN INTERNATIONAL JOURNAL-JESTECH
Main Authors: Abdullah, Ezmin; Dimyati, Kaharudin; Muhamad, Wan Norsyafizan W.; Shuhaimi, Nurain Izzati; Mohamad, Roslina; Hidayat, Nabil M.
Format: Article; Early Access
Language:English
Published: ELSEVIER - DIVISION REED ELSEVIER INDIA PVT LTD 2024
Subjects:
Online Access:https://www-webofscience-com.uitm.idm.oclc.org/wos/woscc/full-record/WOS:001162239300001
author Abdullah
Ezmin; Dimyati
Kaharudin; Muhamad
Wan Norsyafizan W.; Shuhaimi
Nurain Izzati; Mohamad
Roslina; Hidayat
Nabil M.
spellingShingle Abdullah
Ezmin; Dimyati
Kaharudin; Muhamad
Wan Norsyafizan W.; Shuhaimi
Nurain Izzati; Mohamad
Roslina; Hidayat
Nabil M.
Deep learning based asymmetrical autoencoder for PAPR reduction of CP-OFDM systems
Engineering
author_facet Abdullah
Ezmin; Dimyati
Kaharudin; Muhamad
Wan Norsyafizan W.; Shuhaimi
Nurain Izzati; Mohamad
Roslina; Hidayat
Nabil M.
author_sort Abdullah
spelling Abdullah, Ezmin; Dimyati, Kaharudin; Muhamad, Wan Norsyafizan W.; Shuhaimi, Nurain Izzati; Mohamad, Roslina; Hidayat, Nabil M.
Deep learning based asymmetrical autoencoder for PAPR reduction of CP-OFDM systems
ENGINEERING SCIENCE AND TECHNOLOGY-AN INTERNATIONAL JOURNAL-JESTECH
English
Article; Early Access
Adoption of Orthogonal Frequency Division Multiplexing (OFDM) in 5th Generation New Radio (5G NR) as a multicarrier modulation technique allows high data rate transmission with lower complexity. However, problem such as peak to average power ratio (PAPR) has decreased the transmitter efficiency. Recently, several attempts have been made to reduce the high PAPR in OFDM utilizing deep learning (DL) based on autoencoder architecture. However, the proposed autoencoder using symmetrical autoencoder (SAE) is followed by high computational complexity at both transmitter and receiver as well as BER performance degradation. Since 5G NR focuses on massive 5G internet of things eco-system, a flexible carrier spacing is used to support diverse spectrum bands which is afterward named as Cyclic Prefix OFDM (CP-OFDM). In this study, we aimed to contribute to this growing area of research by exploring the potential of our proposed asymmetrical autoencoder (AAE) to reduce high PAPR in the CP-OFDM system. Four AAE models have been developed in this study and the performance of the models were evaluated based on comprehensive conditions such as data training at different corruption levels, cyclic prefix length, upsampling factors and loss function levels. The investigation of AAE in 5G CP-OFDM system has shown superior performance using a 5x1 AAE model that can reduce a substantial amount of PAPR, BER degradation and computational complexity compared to conventional SAE. This study lays the groundwork for future research into the asymmetrical approach of autoencoder especially in 5G and beyond networks.
ELSEVIER - DIVISION REED ELSEVIER INDIA PVT LTD
2215-0986

2024
50

10.1016/j.jestch.2023.101608
Engineering
hybrid
WOS:001162239300001
https://www-webofscience-com.uitm.idm.oclc.org/wos/woscc/full-record/WOS:001162239300001
title Deep learning based asymmetrical autoencoder for PAPR reduction of CP-OFDM systems
title_short Deep learning based asymmetrical autoencoder for PAPR reduction of CP-OFDM systems
title_full Deep learning based asymmetrical autoencoder for PAPR reduction of CP-OFDM systems
title_fullStr Deep learning based asymmetrical autoencoder for PAPR reduction of CP-OFDM systems
title_full_unstemmed Deep learning based asymmetrical autoencoder for PAPR reduction of CP-OFDM systems
title_sort Deep learning based asymmetrical autoencoder for PAPR reduction of CP-OFDM systems
container_title ENGINEERING SCIENCE AND TECHNOLOGY-AN INTERNATIONAL JOURNAL-JESTECH
language English
format Article; Early Access
description Adoption of Orthogonal Frequency Division Multiplexing (OFDM) in 5th Generation New Radio (5G NR) as a multicarrier modulation technique allows high data rate transmission with lower complexity. However, problem such as peak to average power ratio (PAPR) has decreased the transmitter efficiency. Recently, several attempts have been made to reduce the high PAPR in OFDM utilizing deep learning (DL) based on autoencoder architecture. However, the proposed autoencoder using symmetrical autoencoder (SAE) is followed by high computational complexity at both transmitter and receiver as well as BER performance degradation. Since 5G NR focuses on massive 5G internet of things eco-system, a flexible carrier spacing is used to support diverse spectrum bands which is afterward named as Cyclic Prefix OFDM (CP-OFDM). In this study, we aimed to contribute to this growing area of research by exploring the potential of our proposed asymmetrical autoencoder (AAE) to reduce high PAPR in the CP-OFDM system. Four AAE models have been developed in this study and the performance of the models were evaluated based on comprehensive conditions such as data training at different corruption levels, cyclic prefix length, upsampling factors and loss function levels. The investigation of AAE in 5G CP-OFDM system has shown superior performance using a 5x1 AAE model that can reduce a substantial amount of PAPR, BER degradation and computational complexity compared to conventional SAE. This study lays the groundwork for future research into the asymmetrical approach of autoencoder especially in 5G and beyond networks.
publisher ELSEVIER - DIVISION REED ELSEVIER INDIA PVT LTD
issn 2215-0986

publishDate 2024
container_volume 50
container_issue
doi_str_mv 10.1016/j.jestch.2023.101608
topic Engineering
topic_facet Engineering
accesstype hybrid
id WOS:001162239300001
url https://www-webofscience-com.uitm.idm.oclc.org/wos/woscc/full-record/WOS:001162239300001
record_format wos
collection Web of Science (WoS)
_version_ 1809678631981547520