AI-Based EMT Dynamic Model of PV Systems

Suman Debnath; Phani R. V Marthi; Qianxue Xia

doi:10.1109/ISGT-LA56058.2023.10328311

AI-Based EMT Dynamic Model of PV Systems

Suman Debnath, Phani R. V Marthi, Qianxue Xia

Power Systems Resilience

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

1 Scopus citations

Abstract

Several electromagnetic transient (EMT) dynamic modeling methods are available to model systems like photovoltaic (PV) plants, wind power plants, variable-speed drives, among others. The methods include: (a) physics-based models and (b) data-driven models. The physics-based dynamic models may include high-fidelity switched system model and average-value model that both require the control algorithms included in the models. However, manufacturers typically prefer to provide black-box models to avoid disclosing proprietary. One of the solutions to prevent disclosing control algorithms is the use of data-driven dynamic EMT models of PV systems. In this paper, data-driven dynamic EMT model based on artificial intelligence (AI) algorithms are presented. The AI algorithms evaluated include convolutional neural networks, recurrent neural networks, and nonlinear auto-regressive exogenous model. Automation in generating data and training these models is also discussed in this paper. The results generated by the best AI algorithms have been observed to be greater than 95 % accurate.

Original language	English
Title of host publication	2023 IEEE PES Innovative Smart Grid Technologies Latin America, ISGT-LA 2023
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	430-434
Number of pages	5
ISBN (Electronic)	9798350336962
DOIs	https://doi.org/10.1109/ISGT-LA56058.2023.10328311
State	Published - 2023
Event	2023 IEEE PES Innovative Smart Grid Technologies Latin America, ISGT-LA 2023 - San Juan, United States Duration: Nov 6 2023 → Nov 9 2023

Publication series

Name	2023 IEEE PES Innovative Smart Grid Technologies Latin America, ISGT-LA 2023

Conference

Conference	2023 IEEE PES Innovative Smart Grid Technologies Latin America, ISGT-LA 2023
Country/Territory	United States
City	San Juan
Period	11/6/23 → 11/9/23

Funding

Research sponsored by Solar Energy Technologies Office of U.S. Department of Energy. This material is based upon work supported by the U.S. Department of Energy’s Office of Energy Efficiency and Renewable Energy (EERE) under the Solar Energy Technologies Office Award Number 36532. The views expressed herein do not necessarily represent the views of the U.S. Department of Energy or the United States Government.

Keywords

AI
Automation
EMT
PV Plant
Surrogate Model

Access to Document

10.1109/ISGT-LA56058.2023.10328311

Cite this

Debnath, S., V Marthi, P. R., & Xia, Q. (2023). AI-Based EMT Dynamic Model of PV Systems. In 2023 IEEE PES Innovative Smart Grid Technologies Latin America, ISGT-LA 2023 (pp. 430-434). (2023 IEEE PES Innovative Smart Grid Technologies Latin America, ISGT-LA 2023). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ISGT-LA56058.2023.10328311

@inproceedings{1c0d6e9289c444e79f90de9ad91adf5b,

title = "AI-Based EMT Dynamic Model of PV Systems",

abstract = "Several electromagnetic transient (EMT) dynamic modeling methods are available to model systems like photovoltaic (PV) plants, wind power plants, variable-speed drives, among others. The methods include: (a) physics-based models and (b) data-driven models. The physics-based dynamic models may include high-fidelity switched system model and average-value model that both require the control algorithms included in the models. However, manufacturers typically prefer to provide black-box models to avoid disclosing proprietary. One of the solutions to prevent disclosing control algorithms is the use of data-driven dynamic EMT models of PV systems. In this paper, data-driven dynamic EMT model based on artificial intelligence (AI) algorithms are presented. The AI algorithms evaluated include convolutional neural networks, recurrent neural networks, and nonlinear auto-regressive exogenous model. Automation in generating data and training these models is also discussed in this paper. The results generated by the best AI algorithms have been observed to be greater than 95 % accurate.",

keywords = "AI, Automation, EMT, PV Plant, Surrogate Model",

author = "Suman Debnath and {V Marthi}, {Phani R.} and Qianxue Xia",

note = "Publisher Copyright: {\textcopyright} 2023 IEEE.; 2023 IEEE PES Innovative Smart Grid Technologies Latin America, ISGT-LA 2023 ; Conference date: 06-11-2023 Through 09-11-2023",

year = "2023",

doi = "10.1109/ISGT-LA56058.2023.10328311",

language = "English",

series = "2023 IEEE PES Innovative Smart Grid Technologies Latin America, ISGT-LA 2023",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "430--434",

booktitle = "2023 IEEE PES Innovative Smart Grid Technologies Latin America, ISGT-LA 2023",

}

Debnath, S , V Marthi, PR & Xia, Q 2023, AI-Based EMT Dynamic Model of PV Systems. in 2023 IEEE PES Innovative Smart Grid Technologies Latin America, ISGT-LA 2023. 2023 IEEE PES Innovative Smart Grid Technologies Latin America, ISGT-LA 2023, Institute of Electrical and Electronics Engineers Inc., pp. 430-434, 2023 IEEE PES Innovative Smart Grid Technologies Latin America, ISGT-LA 2023, San Juan, United States, 11/6/23. https://doi.org/10.1109/ISGT-LA56058.2023.10328311

AI-Based EMT Dynamic Model of PV Systems. / Debnath, Suman ; V Marthi, Phani R.; Xia, Qianxue.
2023 IEEE PES Innovative Smart Grid Technologies Latin America, ISGT-LA 2023. Institute of Electrical and Electronics Engineers Inc., 2023. p. 430-434 (2023 IEEE PES Innovative Smart Grid Technologies Latin America, ISGT-LA 2023).

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

TY - GEN

T1 - AI-Based EMT Dynamic Model of PV Systems

AU - Debnath, Suman

AU - V Marthi, Phani R.

AU - Xia, Qianxue

PY - 2023

Y1 - 2023

N2 - Several electromagnetic transient (EMT) dynamic modeling methods are available to model systems like photovoltaic (PV) plants, wind power plants, variable-speed drives, among others. The methods include: (a) physics-based models and (b) data-driven models. The physics-based dynamic models may include high-fidelity switched system model and average-value model that both require the control algorithms included in the models. However, manufacturers typically prefer to provide black-box models to avoid disclosing proprietary. One of the solutions to prevent disclosing control algorithms is the use of data-driven dynamic EMT models of PV systems. In this paper, data-driven dynamic EMT model based on artificial intelligence (AI) algorithms are presented. The AI algorithms evaluated include convolutional neural networks, recurrent neural networks, and nonlinear auto-regressive exogenous model. Automation in generating data and training these models is also discussed in this paper. The results generated by the best AI algorithms have been observed to be greater than 95 % accurate.

AB - Several electromagnetic transient (EMT) dynamic modeling methods are available to model systems like photovoltaic (PV) plants, wind power plants, variable-speed drives, among others. The methods include: (a) physics-based models and (b) data-driven models. The physics-based dynamic models may include high-fidelity switched system model and average-value model that both require the control algorithms included in the models. However, manufacturers typically prefer to provide black-box models to avoid disclosing proprietary. One of the solutions to prevent disclosing control algorithms is the use of data-driven dynamic EMT models of PV systems. In this paper, data-driven dynamic EMT model based on artificial intelligence (AI) algorithms are presented. The AI algorithms evaluated include convolutional neural networks, recurrent neural networks, and nonlinear auto-regressive exogenous model. Automation in generating data and training these models is also discussed in this paper. The results generated by the best AI algorithms have been observed to be greater than 95 % accurate.

KW - AI

KW - Automation

KW - EMT

KW - PV Plant

KW - Surrogate Model

UR - http://www.scopus.com/inward/record.url?scp=85180005511&partnerID=8YFLogxK

U2 - 10.1109/ISGT-LA56058.2023.10328311

DO - 10.1109/ISGT-LA56058.2023.10328311

M3 - Conference contribution

AN - SCOPUS:85180005511

T3 - 2023 IEEE PES Innovative Smart Grid Technologies Latin America, ISGT-LA 2023

SP - 430

EP - 434

BT - 2023 IEEE PES Innovative Smart Grid Technologies Latin America, ISGT-LA 2023

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2023 IEEE PES Innovative Smart Grid Technologies Latin America, ISGT-LA 2023

Y2 - 6 November 2023 through 9 November 2023

ER -

AI-Based EMT Dynamic Model of PV Systems

Abstract

Publication series

Conference

Funding

Keywords

Access to Document

Other files and links

Fingerprint

Cite this