Home > Research > Publications & Outputs > Digital Twin Validation with Multi-epoch, Multi...

Electronic data

  • He_RHodes-Leader_Song_2024

    Accepted author manuscript, 459 KB, PDF document

Links

Text available via DOI:

View graph of relations

Digital Twin Validation with Multi-epoch, Multi-variate Output Data

Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSNConference contribution/Paperpeer-review

Published

Standard

Digital Twin Validation with Multi-epoch, Multi-variate Output Data. / He, Linyun; Rhodes-Leader, Luke; Song, Eunhye.
Proceedings of the 2024 Winter Simulation Conference. IEEE, 2025. p. 347-358.

Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSNConference contribution/Paperpeer-review

Harvard

He, L, Rhodes-Leader, L & Song, E 2025, Digital Twin Validation with Multi-epoch, Multi-variate Output Data. in Proceedings of the 2024 Winter Simulation Conference. IEEE, pp. 347-358. https://doi.org/10.1109/WSC63780.2024.10838742

APA

He, L., Rhodes-Leader, L., & Song, E. (2025). Digital Twin Validation with Multi-epoch, Multi-variate Output Data. In Proceedings of the 2024 Winter Simulation Conference (pp. 347-358). IEEE. https://doi.org/10.1109/WSC63780.2024.10838742

Vancouver

He L, Rhodes-Leader L, Song E. Digital Twin Validation with Multi-epoch, Multi-variate Output Data. In Proceedings of the 2024 Winter Simulation Conference. IEEE. 2025. p. 347-358 Epub 2024 Dec 15. doi: 10.1109/WSC63780.2024.10838742

Author

He, Linyun ; Rhodes-Leader, Luke ; Song, Eunhye. / Digital Twin Validation with Multi-epoch, Multi-variate Output Data. Proceedings of the 2024 Winter Simulation Conference. IEEE, 2025. pp. 347-358

Bibtex

@inproceedings{2ee7f656ca254fec8c3c72eb22abbada,
title = "Digital Twin Validation with Multi-epoch, Multi-variate Output Data",
abstract = "This paper studies validation of a simulation-based process digital twin (DT). We assume that at any point the DT is queried, the system state is recorded. Then, the DT simulator is initialized to match the system state and the simulations are run to predict the key performance indicators (KPIs) at the end of each time epoch of interest. Our validation question is if the distribution of the simulated KPIs matches that of the system KPIs at every epoch. Typically, these KPIs are multi-variate random vectors and non-identically distributed across epochs making it difficult to apply the existing validation methods. We devise a hypothesis test that compares the marginal and joint distributions of the KPI vectors, separately, by transforming the multi-epoch data to identically distributed observations. We empirically demonstrate that the test has good power when the system and the simulator sufficiently differ in distribution.",
author = "Linyun He and Luke Rhodes-Leader and Eunhye Song",
year = "2025",
month = jan,
day = "20",
doi = "10.1109/WSC63780.2024.10838742",
language = "English",
isbn = "9798331534219",
pages = "347--358",
booktitle = "Proceedings of the 2024 Winter Simulation Conference",
publisher = "IEEE",

}

RIS

TY - GEN

T1 - Digital Twin Validation with Multi-epoch, Multi-variate Output Data

AU - He, Linyun

AU - Rhodes-Leader, Luke

AU - Song, Eunhye

PY - 2025/1/20

Y1 - 2025/1/20

N2 - This paper studies validation of a simulation-based process digital twin (DT). We assume that at any point the DT is queried, the system state is recorded. Then, the DT simulator is initialized to match the system state and the simulations are run to predict the key performance indicators (KPIs) at the end of each time epoch of interest. Our validation question is if the distribution of the simulated KPIs matches that of the system KPIs at every epoch. Typically, these KPIs are multi-variate random vectors and non-identically distributed across epochs making it difficult to apply the existing validation methods. We devise a hypothesis test that compares the marginal and joint distributions of the KPI vectors, separately, by transforming the multi-epoch data to identically distributed observations. We empirically demonstrate that the test has good power when the system and the simulator sufficiently differ in distribution.

AB - This paper studies validation of a simulation-based process digital twin (DT). We assume that at any point the DT is queried, the system state is recorded. Then, the DT simulator is initialized to match the system state and the simulations are run to predict the key performance indicators (KPIs) at the end of each time epoch of interest. Our validation question is if the distribution of the simulated KPIs matches that of the system KPIs at every epoch. Typically, these KPIs are multi-variate random vectors and non-identically distributed across epochs making it difficult to apply the existing validation methods. We devise a hypothesis test that compares the marginal and joint distributions of the KPI vectors, separately, by transforming the multi-epoch data to identically distributed observations. We empirically demonstrate that the test has good power when the system and the simulator sufficiently differ in distribution.

U2 - 10.1109/WSC63780.2024.10838742

DO - 10.1109/WSC63780.2024.10838742

M3 - Conference contribution/Paper

SN - 9798331534219

SP - 347

EP - 358

BT - Proceedings of the 2024 Winter Simulation Conference

PB - IEEE

ER -