Block adaptive and neural network based digital predistortion and power amplifier performance

Robert Santucci, Andreas Spanias

Research output: Chapter in Book/Report/Conference proceedingConference contribution

2 Citations (Scopus)

Abstract

The purpose of this paper is to compare the methodology and performance of two different techniques for digital predistortion. The first technique is the block adaptive digital predistorter, which operates using a modified leastmean-squares (LMS) algorithm. The second technique uses a feed-forward time-delay neural network to achieve its linearization performance. The performance of each of these techniques is evaluated for an orthogonal frequency-division multiplexing (OFDM) system with 10dB peak-to-average power ratio (PAR). For easy visual inspection of the tradeoffs, enabling preliminary analysis and teaching, a Java-DSP application has been developed. For more detailed analysis, a clustered MATLAB simulation environment has also been developed. By adding higher-ordered terms as inputs to the neural network, the authors have attained additional linearization near maximum power output for specific power amplifier models.

Original languageEnglish (US)
Title of host publicationProceedings of the 8th IASTED International Conference on Signal Processing, Pattern Recognition, and Applications, SPPRA 2011
Pages300-305
Number of pages6
DOIs
StatePublished - 2011
Event8th IASTED International Conference on Signal Processing, Pattern Recognition, and Applications, SPPRA 2011 - Innsbruck, Austria
Duration: Feb 16 2011Feb 18 2011

Other

Other8th IASTED International Conference on Signal Processing, Pattern Recognition, and Applications, SPPRA 2011
CountryAustria
CityInnsbruck
Period2/16/112/18/11

Fingerprint

Power amplifiers
Linearization
Neural networks
Orthogonal frequency division multiplexing
MATLAB
Time delay
Teaching
Inspection

Keywords

  • Block adaptive filters
  • Linearization
  • Neural networks
  • Predistortion
  • RF amplifier

ASJC Scopus subject areas

  • Computer Science Applications
  • Computer Vision and Pattern Recognition
  • Signal Processing

Cite this

Santucci, R., & Spanias, A. (2011). Block adaptive and neural network based digital predistortion and power amplifier performance. In Proceedings of the 8th IASTED International Conference on Signal Processing, Pattern Recognition, and Applications, SPPRA 2011 (pp. 300-305) https://doi.org/10.2316/P.2011.721-035

Block adaptive and neural network based digital predistortion and power amplifier performance. / Santucci, Robert; Spanias, Andreas.

Proceedings of the 8th IASTED International Conference on Signal Processing, Pattern Recognition, and Applications, SPPRA 2011. 2011. p. 300-305.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Santucci, R & Spanias, A 2011, Block adaptive and neural network based digital predistortion and power amplifier performance. in Proceedings of the 8th IASTED International Conference on Signal Processing, Pattern Recognition, and Applications, SPPRA 2011. pp. 300-305, 8th IASTED International Conference on Signal Processing, Pattern Recognition, and Applications, SPPRA 2011, Innsbruck, Austria, 2/16/11. https://doi.org/10.2316/P.2011.721-035
Santucci R, Spanias A. Block adaptive and neural network based digital predistortion and power amplifier performance. In Proceedings of the 8th IASTED International Conference on Signal Processing, Pattern Recognition, and Applications, SPPRA 2011. 2011. p. 300-305 https://doi.org/10.2316/P.2011.721-035
Santucci, Robert ; Spanias, Andreas. / Block adaptive and neural network based digital predistortion and power amplifier performance. Proceedings of the 8th IASTED International Conference on Signal Processing, Pattern Recognition, and Applications, SPPRA 2011. 2011. pp. 300-305
@inproceedings{5dc6e646b13b4acdaa71e67f29da5a42,
title = "Block adaptive and neural network based digital predistortion and power amplifier performance",
abstract = "The purpose of this paper is to compare the methodology and performance of two different techniques for digital predistortion. The first technique is the block adaptive digital predistorter, which operates using a modified leastmean-squares (LMS) algorithm. The second technique uses a feed-forward time-delay neural network to achieve its linearization performance. The performance of each of these techniques is evaluated for an orthogonal frequency-division multiplexing (OFDM) system with 10dB peak-to-average power ratio (PAR). For easy visual inspection of the tradeoffs, enabling preliminary analysis and teaching, a Java-DSP application has been developed. For more detailed analysis, a clustered MATLAB simulation environment has also been developed. By adding higher-ordered terms as inputs to the neural network, the authors have attained additional linearization near maximum power output for specific power amplifier models.",
keywords = "Block adaptive filters, Linearization, Neural networks, Predistortion, RF amplifier",
author = "Robert Santucci and Andreas Spanias",
year = "2011",
doi = "10.2316/P.2011.721-035",
language = "English (US)",
isbn = "9780889868656",
pages = "300--305",
booktitle = "Proceedings of the 8th IASTED International Conference on Signal Processing, Pattern Recognition, and Applications, SPPRA 2011",

}

TY - GEN

T1 - Block adaptive and neural network based digital predistortion and power amplifier performance

AU - Santucci, Robert

AU - Spanias, Andreas

PY - 2011

Y1 - 2011

N2 - The purpose of this paper is to compare the methodology and performance of two different techniques for digital predistortion. The first technique is the block adaptive digital predistorter, which operates using a modified leastmean-squares (LMS) algorithm. The second technique uses a feed-forward time-delay neural network to achieve its linearization performance. The performance of each of these techniques is evaluated for an orthogonal frequency-division multiplexing (OFDM) system with 10dB peak-to-average power ratio (PAR). For easy visual inspection of the tradeoffs, enabling preliminary analysis and teaching, a Java-DSP application has been developed. For more detailed analysis, a clustered MATLAB simulation environment has also been developed. By adding higher-ordered terms as inputs to the neural network, the authors have attained additional linearization near maximum power output for specific power amplifier models.

AB - The purpose of this paper is to compare the methodology and performance of two different techniques for digital predistortion. The first technique is the block adaptive digital predistorter, which operates using a modified leastmean-squares (LMS) algorithm. The second technique uses a feed-forward time-delay neural network to achieve its linearization performance. The performance of each of these techniques is evaluated for an orthogonal frequency-division multiplexing (OFDM) system with 10dB peak-to-average power ratio (PAR). For easy visual inspection of the tradeoffs, enabling preliminary analysis and teaching, a Java-DSP application has been developed. For more detailed analysis, a clustered MATLAB simulation environment has also been developed. By adding higher-ordered terms as inputs to the neural network, the authors have attained additional linearization near maximum power output for specific power amplifier models.

KW - Block adaptive filters

KW - Linearization

KW - Neural networks

KW - Predistortion

KW - RF amplifier

UR - http://www.scopus.com/inward/record.url?scp=79958169893&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=79958169893&partnerID=8YFLogxK

U2 - 10.2316/P.2011.721-035

DO - 10.2316/P.2011.721-035

M3 - Conference contribution

AN - SCOPUS:79958169893

SN - 9780889868656

SP - 300

EP - 305

BT - Proceedings of the 8th IASTED International Conference on Signal Processing, Pattern Recognition, and Applications, SPPRA 2011

ER -