Options
Application of gaussian process regression for data efficient prediction of PCB-based power delivery network impedance features
Publikationstyp
Conference Paper
Date Issued
2024-05
Sprache
English
Journal
SPI 2024 - 28th IEEE Workshop on Signal and Power Integrity, Proceedings
Citation
SPI 2024 - 28th IEEE Workshop on Signal and Power Integrity, Proceedings
Contribution to Conference
Publisher DOI
Scopus ID
Publisher
IEEE
ISBN
979-8-3503-8293-8
In this paper, a data efficient machine learning (ML)-based framework for the prediction of key-features of the power delivery network (PDN) impedance is proposed. Gaussian Process Regression (GPR) is implemented within transfer and active learning loops to explore the potential with regard to data efficiency and accuracy. For a 4 layered printed circuit board (PCB), a prediction accuracy with a normalized root mean squared error (RMSE) of 3 % is achieved for some features including the resonance frequency of the board. The use of transfer learning results in a higher data efficiency and faster convergence. It is shown that reusing data from closer problems reduces the amount of new samples that need to be generated. The higher data efficiency makes ML tools a more attractive approach to speed up PDN design by replacing the expensive electromagnetic (EM) simulations of PCBs.
Subjects
EM simulations
Gaussian Process Regression (GPR)
machine learning (ML)
PCB
PDN design
MLE@TUHH
DDC Class
600: Technology