Sequential Monte Carlo-based fidelity selection in Dynamic-data-driven Adaptive Multi-scale Simulations (DDDAMS)

Nurcin Celik, Young Jun Son

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

4 Citations (Scopus)

Abstract

In DDDAMS paradigm, the fidelity of a complex simulation model adapts to available computational resources by incorporating dynamic data into the executing model, which then steers the measurement process for selective data update. Real-time inferencing for a large-scale system may involve hundreds of sensors for various quantity of interests, which makes it a challenging task considering limited resources. In this work, a Sequential Monte Carlo method (sequential Bayesian inference technique) is proposed and embedded into the simulation to enable its ideal fidelity selection given massive datasets. As dynamic information becomes available, the proposed method makes efficient inferences to determine the sources of abnormality in the system. A parallelization frame is also discussed to further reduce the number of data accesses while maintaining the accuracy of parameter estimates. A prototype DDDAMS involving the proposed algorithm has been successfully implemented for preventive maintenance and part routing scheduling in a semiconductor supply chain.

Original languageEnglish
Title of host publicationProceedings - Winter Simulation Conference
Pages2281-2293
Number of pages13
DOIs
StatePublished - Dec 1 2009
Externally publishedYes
Event2009 Winter Simulation Conference, WSC 2009 - Austin, TX, United States
Duration: Dec 13 2009Dec 16 2009

Other

Other2009 Winter Simulation Conference, WSC 2009
CountryUnited States
CityAustin, TX
Period12/13/0912/16/09

Fingerprint

Sequential Monte Carlo
Multiscale Simulation
Data-driven
Fidelity
Sequential Monte Carlo Methods
Preventive Maintenance
Resources
Preventive maintenance
Bayesian inference
Large-scale Systems
Supply Chain
Parallelization
Supply chains
Large scale systems
Semiconductors
Simulation Model
Routing
Monte Carlo methods
Update
Scheduling

ASJC Scopus subject areas

  • Software
  • Modeling and Simulation
  • Computer Science Applications

Cite this

Sequential Monte Carlo-based fidelity selection in Dynamic-data-driven Adaptive Multi-scale Simulations (DDDAMS). / Celik, Nurcin; Son, Young Jun.

Proceedings - Winter Simulation Conference. 2009. p. 2281-2293 5429195.

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

Celik, N & Son, YJ 2009, Sequential Monte Carlo-based fidelity selection in Dynamic-data-driven Adaptive Multi-scale Simulations (DDDAMS). in Proceedings - Winter Simulation Conference., 5429195, pp. 2281-2293, 2009 Winter Simulation Conference, WSC 2009, Austin, TX, United States, 12/13/09. https://doi.org/10.1109/WSC.2009.5429195
Celik, Nurcin ; Son, Young Jun. / Sequential Monte Carlo-based fidelity selection in Dynamic-data-driven Adaptive Multi-scale Simulations (DDDAMS). Proceedings - Winter Simulation Conference. 2009. pp. 2281-2293
@inproceedings{7c5395be75a94939a99d97005624fb98,
title = "Sequential Monte Carlo-based fidelity selection in Dynamic-data-driven Adaptive Multi-scale Simulations (DDDAMS)",
abstract = "In DDDAMS paradigm, the fidelity of a complex simulation model adapts to available computational resources by incorporating dynamic data into the executing model, which then steers the measurement process for selective data update. Real-time inferencing for a large-scale system may involve hundreds of sensors for various quantity of interests, which makes it a challenging task considering limited resources. In this work, a Sequential Monte Carlo method (sequential Bayesian inference technique) is proposed and embedded into the simulation to enable its ideal fidelity selection given massive datasets. As dynamic information becomes available, the proposed method makes efficient inferences to determine the sources of abnormality in the system. A parallelization frame is also discussed to further reduce the number of data accesses while maintaining the accuracy of parameter estimates. A prototype DDDAMS involving the proposed algorithm has been successfully implemented for preventive maintenance and part routing scheduling in a semiconductor supply chain.",
author = "Nurcin Celik and Son, {Young Jun}",
year = "2009",
month = "12",
day = "1",
doi = "10.1109/WSC.2009.5429195",
language = "English",
isbn = "9781424457700",
pages = "2281--2293",
booktitle = "Proceedings - Winter Simulation Conference",

}

TY - GEN

T1 - Sequential Monte Carlo-based fidelity selection in Dynamic-data-driven Adaptive Multi-scale Simulations (DDDAMS)

AU - Celik, Nurcin

AU - Son, Young Jun

PY - 2009/12/1

Y1 - 2009/12/1

N2 - In DDDAMS paradigm, the fidelity of a complex simulation model adapts to available computational resources by incorporating dynamic data into the executing model, which then steers the measurement process for selective data update. Real-time inferencing for a large-scale system may involve hundreds of sensors for various quantity of interests, which makes it a challenging task considering limited resources. In this work, a Sequential Monte Carlo method (sequential Bayesian inference technique) is proposed and embedded into the simulation to enable its ideal fidelity selection given massive datasets. As dynamic information becomes available, the proposed method makes efficient inferences to determine the sources of abnormality in the system. A parallelization frame is also discussed to further reduce the number of data accesses while maintaining the accuracy of parameter estimates. A prototype DDDAMS involving the proposed algorithm has been successfully implemented for preventive maintenance and part routing scheduling in a semiconductor supply chain.

AB - In DDDAMS paradigm, the fidelity of a complex simulation model adapts to available computational resources by incorporating dynamic data into the executing model, which then steers the measurement process for selective data update. Real-time inferencing for a large-scale system may involve hundreds of sensors for various quantity of interests, which makes it a challenging task considering limited resources. In this work, a Sequential Monte Carlo method (sequential Bayesian inference technique) is proposed and embedded into the simulation to enable its ideal fidelity selection given massive datasets. As dynamic information becomes available, the proposed method makes efficient inferences to determine the sources of abnormality in the system. A parallelization frame is also discussed to further reduce the number of data accesses while maintaining the accuracy of parameter estimates. A prototype DDDAMS involving the proposed algorithm has been successfully implemented for preventive maintenance and part routing scheduling in a semiconductor supply chain.

UR - http://www.scopus.com/inward/record.url?scp=77951545828&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=77951545828&partnerID=8YFLogxK

U2 - 10.1109/WSC.2009.5429195

DO - 10.1109/WSC.2009.5429195

M3 - Conference contribution

SN - 9781424457700

SP - 2281

EP - 2293

BT - Proceedings - Winter Simulation Conference

ER -