TY - GEN
T1 - A Modified Polynomial Chaos Modeling Approach for Uncertainty Quantification
AU - Dolatsara, Majid Ahadi
AU - Varma, Ambrish
AU - Keshavan, Kumar
AU - Swaminathan, Madhavan
N1 - Publisher Copyright:
© 2019 ACES.
PY - 2019/5/10
Y1 - 2019/5/10
N2 - Uncertainty quantification is a key element for modeling high speed circuits, which is often done with Monte Carlo analysis. However, because this method is computationally expensive, new approaches with higher efficiency have been developed. Many popular methods are based on the surrogate models developed with Polynomial Chaos theory. However, size of these models can be prohibitively large for realistic examples. Hence, this paper provides a novel methodology to use an ensemble of weaker models to improve efficiency. Finally, a numerical example with a DDR4 topology is provided.
AB - Uncertainty quantification is a key element for modeling high speed circuits, which is often done with Monte Carlo analysis. However, because this method is computationally expensive, new approaches with higher efficiency have been developed. Many popular methods are based on the surrogate models developed with Polynomial Chaos theory. However, size of these models can be prohibitively large for realistic examples. Hence, this paper provides a novel methodology to use an ensemble of weaker models to improve efficiency. Finally, a numerical example with a DDR4 topology is provided.
UR - http://www.scopus.com/inward/record.url?scp=85066490728&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85066490728&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:85066490728
T3 - 2019 International Applied Computational Electromagnetics Society Symposium in Miami, ACES-Miami 2019
BT - 2019 International Applied Computational Electromagnetics Society Symposium in Miami, ACES-Miami 2019
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2019 International Applied Computational Electromagnetics Society Symposium in Miami, ACES-Miami 2019
Y2 - 14 April 2019 through 18 April 2019
ER -