Steady-state quantile parameter estimation: An empirical comparison of stochastic kriging and quantile regression

Jennifer Bekki, Xi Chen, Demet Batur

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

    7 Citations (Scopus)

    Abstract

    The time required to execute simulation models of modern production systems remains high even with todays computing power, particularly when what-if analyses need to be performed to investigate the impact of controllable system input variables on an output performance measure. Compared to mean and variance which are frequently used in practice, quantiles provide a more complete picture of the performance of the underlying system. Nevertheless, quantiles are more difficult to estimate efficiently through stochastic simulation. Stochastic kriging (SK) and quantile regression (QR) are two promising metamodeling tools for addressing this challenge. Both approximate the functional relationship between the quantile parameter of a random output (e.g., cycle time) and multiple input variables (e.g., start rate, unloading times). In this paper, we compare performances of SK and QR on steady-state quantile parameter estimation. Results are presented from simulations of an M/M/1 queue and a more realistic model of a semiconductor manufacturing system.

    Original languageEnglish (US)
    Title of host publicationProceedings - Winter Simulation Conference
    PublisherInstitute of Electrical and Electronics Engineers Inc.
    Pages3880-3891
    Number of pages12
    Volume2015-January
    ISBN (Print)9781479974863
    DOIs
    StatePublished - Jan 23 2015
    Event2014 Winter Simulation Conference, WSC 2014 - Savannah, United States
    Duration: Dec 7 2014Dec 10 2014

    Other

    Other2014 Winter Simulation Conference, WSC 2014
    CountryUnited States
    CitySavannah
    Period12/7/1412/10/14

    Fingerprint

    Quantile Estimation
    Quantile Regression
    Kriging
    Quantile
    Parameter estimation
    Parameter Estimation
    Unloading
    M/M/1 Queue
    Semiconductor Manufacturing
    Functional Relationship
    Metamodeling
    Output
    Stochastic Simulation
    Production Systems
    Semiconductor materials
    Performance Measures
    Simulation Model
    Computing
    Estimate
    Simulation

    ASJC Scopus subject areas

    • Software
    • Modeling and Simulation
    • Computer Science Applications

    Cite this

    Bekki, J., Chen, X., & Batur, D. (2015). Steady-state quantile parameter estimation: An empirical comparison of stochastic kriging and quantile regression. In Proceedings - Winter Simulation Conference (Vol. 2015-January, pp. 3880-3891). [7020214] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/WSC.2014.7020214

    Steady-state quantile parameter estimation : An empirical comparison of stochastic kriging and quantile regression. / Bekki, Jennifer; Chen, Xi; Batur, Demet.

    Proceedings - Winter Simulation Conference. Vol. 2015-January Institute of Electrical and Electronics Engineers Inc., 2015. p. 3880-3891 7020214.

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

    Bekki, J, Chen, X & Batur, D 2015, Steady-state quantile parameter estimation: An empirical comparison of stochastic kriging and quantile regression. in Proceedings - Winter Simulation Conference. vol. 2015-January, 7020214, Institute of Electrical and Electronics Engineers Inc., pp. 3880-3891, 2014 Winter Simulation Conference, WSC 2014, Savannah, United States, 12/7/14. https://doi.org/10.1109/WSC.2014.7020214
    Bekki J, Chen X, Batur D. Steady-state quantile parameter estimation: An empirical comparison of stochastic kriging and quantile regression. In Proceedings - Winter Simulation Conference. Vol. 2015-January. Institute of Electrical and Electronics Engineers Inc. 2015. p. 3880-3891. 7020214 https://doi.org/10.1109/WSC.2014.7020214
    Bekki, Jennifer ; Chen, Xi ; Batur, Demet. / Steady-state quantile parameter estimation : An empirical comparison of stochastic kriging and quantile regression. Proceedings - Winter Simulation Conference. Vol. 2015-January Institute of Electrical and Electronics Engineers Inc., 2015. pp. 3880-3891
    @inproceedings{b02c71f4883647e8acef4a7369de3c8a,
    title = "Steady-state quantile parameter estimation: An empirical comparison of stochastic kriging and quantile regression",
    abstract = "The time required to execute simulation models of modern production systems remains high even with todays computing power, particularly when what-if analyses need to be performed to investigate the impact of controllable system input variables on an output performance measure. Compared to mean and variance which are frequently used in practice, quantiles provide a more complete picture of the performance of the underlying system. Nevertheless, quantiles are more difficult to estimate efficiently through stochastic simulation. Stochastic kriging (SK) and quantile regression (QR) are two promising metamodeling tools for addressing this challenge. Both approximate the functional relationship between the quantile parameter of a random output (e.g., cycle time) and multiple input variables (e.g., start rate, unloading times). In this paper, we compare performances of SK and QR on steady-state quantile parameter estimation. Results are presented from simulations of an M/M/1 queue and a more realistic model of a semiconductor manufacturing system.",
    author = "Jennifer Bekki and Xi Chen and Demet Batur",
    year = "2015",
    month = "1",
    day = "23",
    doi = "10.1109/WSC.2014.7020214",
    language = "English (US)",
    isbn = "9781479974863",
    volume = "2015-January",
    pages = "3880--3891",
    booktitle = "Proceedings - Winter Simulation Conference",
    publisher = "Institute of Electrical and Electronics Engineers Inc.",

    }

    TY - GEN

    T1 - Steady-state quantile parameter estimation

    T2 - An empirical comparison of stochastic kriging and quantile regression

    AU - Bekki, Jennifer

    AU - Chen, Xi

    AU - Batur, Demet

    PY - 2015/1/23

    Y1 - 2015/1/23

    N2 - The time required to execute simulation models of modern production systems remains high even with todays computing power, particularly when what-if analyses need to be performed to investigate the impact of controllable system input variables on an output performance measure. Compared to mean and variance which are frequently used in practice, quantiles provide a more complete picture of the performance of the underlying system. Nevertheless, quantiles are more difficult to estimate efficiently through stochastic simulation. Stochastic kriging (SK) and quantile regression (QR) are two promising metamodeling tools for addressing this challenge. Both approximate the functional relationship between the quantile parameter of a random output (e.g., cycle time) and multiple input variables (e.g., start rate, unloading times). In this paper, we compare performances of SK and QR on steady-state quantile parameter estimation. Results are presented from simulations of an M/M/1 queue and a more realistic model of a semiconductor manufacturing system.

    AB - The time required to execute simulation models of modern production systems remains high even with todays computing power, particularly when what-if analyses need to be performed to investigate the impact of controllable system input variables on an output performance measure. Compared to mean and variance which are frequently used in practice, quantiles provide a more complete picture of the performance of the underlying system. Nevertheless, quantiles are more difficult to estimate efficiently through stochastic simulation. Stochastic kriging (SK) and quantile regression (QR) are two promising metamodeling tools for addressing this challenge. Both approximate the functional relationship between the quantile parameter of a random output (e.g., cycle time) and multiple input variables (e.g., start rate, unloading times). In this paper, we compare performances of SK and QR on steady-state quantile parameter estimation. Results are presented from simulations of an M/M/1 queue and a more realistic model of a semiconductor manufacturing system.

    UR - http://www.scopus.com/inward/record.url?scp=84940473849&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=84940473849&partnerID=8YFLogxK

    U2 - 10.1109/WSC.2014.7020214

    DO - 10.1109/WSC.2014.7020214

    M3 - Conference contribution

    AN - SCOPUS:84940473849

    SN - 9781479974863

    VL - 2015-January

    SP - 3880

    EP - 3891

    BT - Proceedings - Winter Simulation Conference

    PB - Institute of Electrical and Electronics Engineers Inc.

    ER -