Academic Bibliography

 Search 200 years of publications by Ghent University researchers.
Advanced search
2 files | 478.84 KB
Add to list
  1. Search results
  2. Data-efficient bayesian optimization ...

Data-efficient bayesian optimization with constraints for power amplifier design

Nicolas Knudde, Ivo Couckuyt (UGent) , Domenico Spina (UGent) , K. Lukasik, P. Barmuta, D. Schreurs and Tom Dhaene (UGent)
(2018) 2018 IEEE MTT-S INTERNATIONAL CONFERENCE ON NUMERICAL ELECTROMAGNETIC AND MULTIPHYSICS MODELING AND OPTIMIZATION (NEMO). p.1-3
Author
Organization
Abstract
Finding the optimal working conditions for non-linear electrical components under large signal stimuli can be challenging, mainly due to the high number of input dimensions and multiple local minima of the goal function. In this paper a Bayesian optimization method is applied in order to limit the number of evaluations by a commercial harmonic balance simulator. The method is applied to amplifier optimization utilizing Wolsfspeed CGH40010F GaN HEMT, for which input power, bias voltages and load at fundamental harmonic frequencies are changed in order to maximize for combined efficiency, gain, and output power. The optimum is found already after 80 iterations.
Keywords
Bayesian optimization, Gaussian process, harmonic balance, load-pull, transistor

Downloads

  • Download
    (...).pdf
    • full text (Published version)
    • |
    • UGent only
    • |
    • PDF
    • |
    • 244.49 KB
  • Download
    7264 i.pdf
    • full text (Accepted manuscript)
    • |
    • open access
    • |
    • PDF
    • |
    • 234.35 KB

Citation

Please use this url to cite or link to this publication:

MLA
Knudde, Nicolas, et al. “Data-Efficient Bayesian Optimization with Constraints for Power Amplifier Design.” 2018 IEEE MTT-S INTERNATIONAL CONFERENCE ON NUMERICAL ELECTROMAGNETIC AND MULTIPHYSICS MODELING AND OPTIMIZATION (NEMO), 2018, pp. 1–3.
APA
Knudde, N., Couckuyt, I., Spina, D., Lukasik, K., Barmuta, P., Schreurs, D., & Dhaene, T. (2018). Data-efficient bayesian optimization with constraints for power amplifier design. 2018 IEEE MTT-S INTERNATIONAL CONFERENCE ON NUMERICAL ELECTROMAGNETIC AND MULTIPHYSICS MODELING AND OPTIMIZATION (NEMO), 1–3.
Chicago author-date
Knudde, Nicolas, Ivo Couckuyt, Domenico Spina, K. Lukasik, P. Barmuta, D. Schreurs, and Tom Dhaene. 2018. “Data-Efficient Bayesian Optimization with Constraints for Power Amplifier Design.” In 2018 IEEE MTT-S INTERNATIONAL CONFERENCE ON NUMERICAL ELECTROMAGNETIC AND MULTIPHYSICS MODELING AND OPTIMIZATION (NEMO), 1–3.
Chicago author-date (all authors)
Knudde, Nicolas, Ivo Couckuyt, Domenico Spina, K. Lukasik, P. Barmuta, D. Schreurs, and Tom Dhaene. 2018. “Data-Efficient Bayesian Optimization with Constraints for Power Amplifier Design.” In 2018 IEEE MTT-S INTERNATIONAL CONFERENCE ON NUMERICAL ELECTROMAGNETIC AND MULTIPHYSICS MODELING AND OPTIMIZATION (NEMO), 1–3.
Vancouver
1.
Knudde N, Couckuyt I, Spina D, Lukasik K, Barmuta P, Schreurs D, et al. Data-efficient bayesian optimization with constraints for power amplifier design. In: 2018 IEEE MTT-S INTERNATIONAL CONFERENCE ON NUMERICAL ELECTROMAGNETIC AND MULTIPHYSICS MODELING AND OPTIMIZATION (NEMO). 2018. p. 1–3.
IEEE
[1]
N. Knudde et al., “Data-efficient bayesian optimization with constraints for power amplifier design,” in 2018 IEEE MTT-S INTERNATIONAL CONFERENCE ON NUMERICAL ELECTROMAGNETIC AND MULTIPHYSICS MODELING AND OPTIMIZATION (NEMO), Reykjavik, Iceland, 2018, pp. 1–3.
@inproceedings{8573080,
  abstract     = {{Finding the optimal working conditions for non-linear electrical components under large signal stimuli can be challenging, mainly due to the high number of input dimensions and multiple local minima of the goal function. In this paper a Bayesian optimization method is applied in order to limit the number of evaluations by a commercial harmonic balance simulator. The method is applied to amplifier optimization utilizing Wolsfspeed CGH40010F GaN HEMT, for which input power, bias voltages and load at fundamental harmonic frequencies are changed in order to maximize for combined efficiency, gain, and output power. The optimum is found already after 80 iterations.}},
  author       = {{Knudde, Nicolas and Couckuyt, Ivo and Spina, Domenico and Lukasik, K. and Barmuta, P. and Schreurs, D. and Dhaene, Tom}},
  booktitle    = {{2018 IEEE MTT-S INTERNATIONAL CONFERENCE ON NUMERICAL ELECTROMAGNETIC AND MULTIPHYSICS MODELING AND OPTIMIZATION (NEMO)}},
  isbn         = {{9781538652039}},
  keywords     = {{Bayesian optimization,Gaussian process,harmonic balance,load-pull,transistor}},
  language     = {{eng}},
  location     = {{Reykjavik, Iceland}},
  pages        = {{1--3}},
  title        = {{Data-efficient bayesian optimization with constraints for power amplifier design}},
  year         = {{2018}},
}