Neural Network-based scheme for PAPR reduction in OFDM Systems

Diego Reinoso-Chisaguano; Felipe Grijalva; Martha Cecilia Paredes Paredes; Jorge Carvajal-Rodriguez

doi:10.1109/ETCM48019.2019.9014895

Neural Network-based scheme for PAPR reduction in OFDM Systems

Diego Reinoso-Chisaguano, Felipe Grijalva, Martha Cecilia Paredes Paredes, Jorge Carvajal-Rodriguez

Escuela Politecnica Nacional

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

1 Scopus citations

Abstract

This paper proposes a neural network-based scheme for Peak-to-Average Power Ratio (PAPR) reduction which also replaces the Inverse Fast Fourier Transform (IFFT) block of an Orthogonal Frequency Division Multiplexing (OFDM) transmitter. The scheme is composed by one neural network per subcarrier, which are implemented only in the transmitter. The training inputs of each neural network are frequency-domain OFDM symbols and the outputs are time-domain PAPR reduced OFDM symbols obtained using a Branch-and-Bound Constellation Extension (BBCE) scheme. The results show that our scheme achieves a PAPR reduction and Bit Error Rate (BER) similar to constellation shaping techniques but with reduced complexity.

Original language	English
Title of host publication	2019 IEEE 4th Ecuador Technical Chapters Meeting, ETCM 2019
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	9781728137643
DOIs	https://doi.org/10.1109/ETCM48019.2019.9014895
State	Published - Nov 2019
Externally published	Yes
Event	4th IEEE Ecuador Technical Chapters Meeting, ETCM 2019 - Guayaquil, Ecuador Duration: 13 Nov 2019 → 15 Nov 2019

Publication series

Name	2019 IEEE 4th Ecuador Technical Chapters Meeting, ETCM 2019

Conference

Conference	4th IEEE Ecuador Technical Chapters Meeting, ETCM 2019
Country/Territory	Ecuador
City	Guayaquil
Period	13/11/19 → 15/11/19

Keywords

BBCE
Neural Networks
OFDM
PAPR

Access to Document

10.1109/ETCM48019.2019.9014895

Cite this

Reinoso-Chisaguano, D., Grijalva, F., Paredes, M. C. P., & Carvajal-Rodriguez, J. (2019). Neural Network-based scheme for PAPR reduction in OFDM Systems. In 2019 IEEE 4th Ecuador Technical Chapters Meeting, ETCM 2019 Article 9014895 (2019 IEEE 4th Ecuador Technical Chapters Meeting, ETCM 2019). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ETCM48019.2019.9014895

@inproceedings{cade034059ce44b9a5147e0391ddf0cb,

title = "Neural Network-based scheme for PAPR reduction in OFDM Systems",

abstract = "This paper proposes a neural network-based scheme for Peak-to-Average Power Ratio (PAPR) reduction which also replaces the Inverse Fast Fourier Transform (IFFT) block of an Orthogonal Frequency Division Multiplexing (OFDM) transmitter. The scheme is composed by one neural network per subcarrier, which are implemented only in the transmitter. The training inputs of each neural network are frequency-domain OFDM symbols and the outputs are time-domain PAPR reduced OFDM symbols obtained using a Branch-and-Bound Constellation Extension (BBCE) scheme. The results show that our scheme achieves a PAPR reduction and Bit Error Rate (BER) similar to constellation shaping techniques but with reduced complexity.",

keywords = "BBCE, Neural Networks, OFDM, PAPR",

author = "Diego Reinoso-Chisaguano and Felipe Grijalva and Paredes, {Martha Cecilia Paredes} and Jorge Carvajal-Rodriguez",

note = "Publisher Copyright: {\textcopyright} 2019 IEEE.; 4th IEEE Ecuador Technical Chapters Meeting, ETCM 2019 ; Conference date: 13-11-2019 Through 15-11-2019",

year = "2019",

month = nov,

doi = "10.1109/ETCM48019.2019.9014895",

language = "Ingl{\'e}s",

series = "2019 IEEE 4th Ecuador Technical Chapters Meeting, ETCM 2019",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

booktitle = "2019 IEEE 4th Ecuador Technical Chapters Meeting, ETCM 2019",

}

Reinoso-Chisaguano, D, Grijalva, F, Paredes, MCP & Carvajal-Rodriguez, J 2019, Neural Network-based scheme for PAPR reduction in OFDM Systems. in 2019 IEEE 4th Ecuador Technical Chapters Meeting, ETCM 2019., 9014895, 2019 IEEE 4th Ecuador Technical Chapters Meeting, ETCM 2019, Institute of Electrical and Electronics Engineers Inc., 4th IEEE Ecuador Technical Chapters Meeting, ETCM 2019, Guayaquil, Ecuador, 13/11/19. https://doi.org/10.1109/ETCM48019.2019.9014895

Neural Network-based scheme for PAPR reduction in OFDM Systems. / Reinoso-Chisaguano, Diego; Grijalva, Felipe; Paredes, Martha Cecilia Paredes et al.
2019 IEEE 4th Ecuador Technical Chapters Meeting, ETCM 2019. Institute of Electrical and Electronics Engineers Inc., 2019. 9014895 (2019 IEEE 4th Ecuador Technical Chapters Meeting, ETCM 2019).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Neural Network-based scheme for PAPR reduction in OFDM Systems

AU - Reinoso-Chisaguano, Diego

AU - Grijalva, Felipe

AU - Paredes, Martha Cecilia Paredes

AU - Carvajal-Rodriguez, Jorge

PY - 2019/11

Y1 - 2019/11

N2 - This paper proposes a neural network-based scheme for Peak-to-Average Power Ratio (PAPR) reduction which also replaces the Inverse Fast Fourier Transform (IFFT) block of an Orthogonal Frequency Division Multiplexing (OFDM) transmitter. The scheme is composed by one neural network per subcarrier, which are implemented only in the transmitter. The training inputs of each neural network are frequency-domain OFDM symbols and the outputs are time-domain PAPR reduced OFDM symbols obtained using a Branch-and-Bound Constellation Extension (BBCE) scheme. The results show that our scheme achieves a PAPR reduction and Bit Error Rate (BER) similar to constellation shaping techniques but with reduced complexity.

AB - This paper proposes a neural network-based scheme for Peak-to-Average Power Ratio (PAPR) reduction which also replaces the Inverse Fast Fourier Transform (IFFT) block of an Orthogonal Frequency Division Multiplexing (OFDM) transmitter. The scheme is composed by one neural network per subcarrier, which are implemented only in the transmitter. The training inputs of each neural network are frequency-domain OFDM symbols and the outputs are time-domain PAPR reduced OFDM symbols obtained using a Branch-and-Bound Constellation Extension (BBCE) scheme. The results show that our scheme achieves a PAPR reduction and Bit Error Rate (BER) similar to constellation shaping techniques but with reduced complexity.

KW - BBCE

KW - Neural Networks

KW - OFDM

KW - PAPR

UR - http://www.scopus.com/inward/record.url?scp=85082005628&partnerID=8YFLogxK

U2 - 10.1109/ETCM48019.2019.9014895

DO - 10.1109/ETCM48019.2019.9014895

M3 - Contribución a la conferencia

AN - SCOPUS:85082005628

T3 - 2019 IEEE 4th Ecuador Technical Chapters Meeting, ETCM 2019

BT - 2019 IEEE 4th Ecuador Technical Chapters Meeting, ETCM 2019

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 4th IEEE Ecuador Technical Chapters Meeting, ETCM 2019

Y2 - 13 November 2019 through 15 November 2019

ER -

Neural Network-based scheme for PAPR reduction in OFDM Systems

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this