Comparison of Selected Support Vector Machine Approaches for Stochastic Power Electronic Circuit Simulation with Parasitics

Karol Niewiadomski; Sharmila Sumsurooah; David W.P. Thomas

doi:10.1109/EMC/SI/PI/EMCEurope52599.2021.9559258

Comparison of Selected Support Vector Machine Approaches for Stochastic Power Electronic Circuit Simulation with Parasitics

Karol Niewiadomski, Sharmila Sumsurooah, David W.P. Thomas

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

2 Citations (Scopus)

18 Downloads (Pure)

Abstract

This paper provides a comparison between op-timization methods used for tuning the hyperparameters of Support Vector Machine model in a stochastic circuit simulation for conducted interference. The methodology is used to create a surrogate model of the frequency and amplitude of the dominant mode of the interference, which is a result of presence of parasitics in the considered switching circuit. Optimization algorithms are compared by obtaining the computational time and by computing a posteriori error of their predictions. The best optimization algorithm in the example provided here is found to be the quasi-Newton Broyden–Fletcher–Goldfarb–Shanno algorithm.

Original language	English
Title of host publication	2021 IEEE International Joint EMC/SI/PI and EMC Europe Symposium
Publisher	IEEE
Pages	591-596
Number of pages	6
ISBN (Print)	978-1-6654-4889-5
DOIs	https://doi.org/10.1109/EMC/SI/PI/EMCEurope52599.2021.9559258
Publication status	Published - 13 Aug 2021
Externally published	Yes
Event	2021 Joint IEEE International symposium on electromagnetic compability, signal & power integrity, and EMC Europe, EMC+SIPI 2021 - Virtual, Raleigh, United States Duration: 26 Jul 2021 → 20 Aug 2021 https://www.emc2021.emcss.org/

Conference

Conference	2021 Joint IEEE International symposium on electromagnetic compability, signal & power integrity, and EMC Europe, EMC+SIPI 2021
Abbreviated title	EMC+SIPI 2021
Country/Territory	United States
City	Raleigh
Period	26/07/21 → 20/08/21
Internet address	https://www.emc2021.emcss.org/

Keywords

Support vector machines
Computational modeling
Stochastic processes
Interference
Prediction algorithms
Integrated circuit modeling
Kernel

Access to Document

10.1109/EMC/SI/PI/EMCEurope52599.2021.9559258

Comparison_of_Selected_NiewiadomskiAccepted author version, 561 KB

https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=9559258

Cite this

@inproceedings{b43bbe35a2af458fbf2ce3726274a5cd,

title = "Comparison of Selected Support Vector Machine Approaches for Stochastic Power Electronic Circuit Simulation with Parasitics",

abstract = "This paper provides a comparison between op-timization methods used for tuning the hyperparameters of Support Vector Machine model in a stochastic circuit simulation for conducted interference. The methodology is used to create a surrogate model of the frequency and amplitude of the dominant mode of the interference, which is a result of presence of parasitics in the considered switching circuit. Optimization algorithms are compared by obtaining the computational time and by computing a posteriori error of their predictions. The best optimization algorithm in the example provided here is found to be the quasi-Newton Broyden–Fletcher–Goldfarb–Shanno algorithm.",

keywords = "Support vector machines, Computational modeling, Stochastic processes, Interference, Prediction algorithms, Integrated circuit modeling, Kernel",

author = "Karol Niewiadomski and Sharmila Sumsurooah and Thomas, {David W.P.}",

year = "2021",

month = aug,

day = "13",

doi = "10.1109/EMC/SI/PI/EMCEurope52599.2021.9559258",

language = "English",

isbn = "978-1-6654-4889-5",

pages = "591--596",

booktitle = "2021 IEEE International Joint EMC/SI/PI and EMC Europe Symposium",

publisher = "IEEE",

address = "United States",

note = "2021 Joint IEEE International symposium on electromagnetic compability, signal & power integrity, and EMC Europe, EMC+SIPI 2021, EMC+SIPI 2021 ; Conference date: 26-07-2021 Through 20-08-2021",

url = "https://www.emc2021.emcss.org/",

}

Niewiadomski, K, Sumsurooah, S & Thomas, DWP 2021, Comparison of Selected Support Vector Machine Approaches for Stochastic Power Electronic Circuit Simulation with Parasitics. in 2021 IEEE International Joint EMC/SI/PI and EMC Europe Symposium., 9559258, IEEE, pp. 591-596, 2021 Joint IEEE International symposium on electromagnetic compability, signal & power integrity, and EMC Europe, EMC+SIPI 2021, Raleigh, North Carolina, United States, 26/07/21. https://doi.org/10.1109/EMC/SI/PI/EMCEurope52599.2021.9559258

Comparison of Selected Support Vector Machine Approaches for Stochastic Power Electronic Circuit Simulation with Parasitics. / Niewiadomski, Karol; Sumsurooah, Sharmila; Thomas, David W.P.
2021 IEEE International Joint EMC/SI/PI and EMC Europe Symposium. IEEE, 2021. p. 591-596 9559258.

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

TY - GEN

T1 - Comparison of Selected Support Vector Machine Approaches for Stochastic Power Electronic Circuit Simulation with Parasitics

AU - Niewiadomski, Karol

AU - Sumsurooah, Sharmila

AU - Thomas, David W.P.

PY - 2021/8/13

Y1 - 2021/8/13

N2 - This paper provides a comparison between op-timization methods used for tuning the hyperparameters of Support Vector Machine model in a stochastic circuit simulation for conducted interference. The methodology is used to create a surrogate model of the frequency and amplitude of the dominant mode of the interference, which is a result of presence of parasitics in the considered switching circuit. Optimization algorithms are compared by obtaining the computational time and by computing a posteriori error of their predictions. The best optimization algorithm in the example provided here is found to be the quasi-Newton Broyden–Fletcher–Goldfarb–Shanno algorithm.

AB - This paper provides a comparison between op-timization methods used for tuning the hyperparameters of Support Vector Machine model in a stochastic circuit simulation for conducted interference. The methodology is used to create a surrogate model of the frequency and amplitude of the dominant mode of the interference, which is a result of presence of parasitics in the considered switching circuit. Optimization algorithms are compared by obtaining the computational time and by computing a posteriori error of their predictions. The best optimization algorithm in the example provided here is found to be the quasi-Newton Broyden–Fletcher–Goldfarb–Shanno algorithm.

KW - Support vector machines

KW - Computational modeling

KW - Stochastic processes

KW - Interference

KW - Prediction algorithms

KW - Integrated circuit modeling

KW - Kernel

UR - https://ieeexplore.ieee.org/document/9559258/

U2 - 10.1109/EMC/SI/PI/EMCEurope52599.2021.9559258

DO - 10.1109/EMC/SI/PI/EMCEurope52599.2021.9559258

M3 - Conference contribution

SN - 978-1-6654-4889-5

SP - 591

EP - 596

BT - 2021 IEEE International Joint EMC/SI/PI and EMC Europe Symposium

PB - IEEE

T2 - 2021 Joint IEEE International symposium on electromagnetic compability, signal & power integrity, and EMC Europe, EMC+SIPI 2021

Y2 - 26 July 2021 through 20 August 2021

ER -

Comparison of Selected Support Vector Machine Approaches for Stochastic Power Electronic Circuit Simulation with Parasitics

Abstract

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this