Transfer Learning for Identifying Impedance Estimation in Voltage Source Inverters

Mengfan Zhang; Xiongfei Wang; Dongsheng Yang; Zihao Cui; Mads Grasboll Christensen

doi:10.1109/ECCE44975.2020.9236090

Transfer Learning for Identifying Impedance Estimation in Voltage Source Inverters

Mengfan Zhang
, Xiongfei Wang
, Dongsheng Yang
, Zihao Cui
, Mads Grasboll Christensen

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

24 Citations (Scopus)

Abstract

The black-box impedance model of the voltage source inverters (VSIs) can be directly identified at the converter terminal without access to its internal control details, which greatly facilitate the converter-grid interactions. However, since the converter is inherently a nonlinear system, the measured converter impedance model will change along with the operating point. As the limited data amount in practical industrial applications, the existing impedance identification method cannot capture this operating point-dependent feature of the impedance model. In this paper, the model-based transfer learning method is employed to generate the operating-point dependent impedance model. This method can significantly reduce the required data amount used in model training so that the machine learning-based method could be applied for the practical industrial application. The comparison results confirm the accuracy of the impedance model obtained by this data-driven impedance identification method.

Original language	English
Title of host publication	2020 IEEE Energy Conversion Congress and Exposition (ECCE)
Publisher	Institute of Electrical and Electronics Engineers
Pages	6170-6174
Number of pages	5
ISBN (Electronic)	9781728158266
DOIs	https://doi.org/10.1109/ECCE44975.2020.9236090
Publication status	Published - 30 Oct 2020
Event	12th Annual IEEE Energy Conversion Congress and Exposition, ECCE 2020 - Virtual, Detroit, United States Duration: 11 Oct 2020 → 15 Oct 2020

Conference

Conference	12th Annual IEEE Energy Conversion Congress and Exposition, ECCE 2020
Country/Territory	United States
City	Virtual, Detroit
Period	11/10/20 → 15/10/20

Keywords

Deep neural network
impedance identification
operating point variation
transfer learning
voltage source inverter

Access to Document

10.1109/ECCE44975.2020.9236090

Cite this

@inproceedings{4a4bce818a1b4dcd85771941435c790e,

title = "Transfer Learning for Identifying Impedance Estimation in Voltage Source Inverters",

abstract = "The black-box impedance model of the voltage source inverters (VSIs) can be directly identified at the converter terminal without access to its internal control details, which greatly facilitate the converter-grid interactions. However, since the converter is inherently a nonlinear system, the measured converter impedance model will change along with the operating point. As the limited data amount in practical industrial applications, the existing impedance identification method cannot capture this operating point-dependent feature of the impedance model. In this paper, the model-based transfer learning method is employed to generate the operating-point dependent impedance model. This method can significantly reduce the required data amount used in model training so that the machine learning-based method could be applied for the practical industrial application. The comparison results confirm the accuracy of the impedance model obtained by this data-driven impedance identification method.",

keywords = "Deep neural network, impedance identification, operating point variation, transfer learning, voltage source inverter",

author = "Mengfan Zhang and Xiongfei Wang and Dongsheng Yang and Zihao Cui and Christensen, \{Mads Grasboll\}",

note = "Publisher Copyright: {\textcopyright} 2020 IEEE.; 12th Annual IEEE Energy Conversion Congress and Exposition, ECCE 2020 ; Conference date: 11-10-2020 Through 15-10-2020",

year = "2020",

month = oct,

day = "30",

doi = "10.1109/ECCE44975.2020.9236090",

language = "English",

pages = "6170--6174",

booktitle = "2020 IEEE Energy Conversion Congress and Exposition (ECCE)",

publisher = "Institute of Electrical and Electronics Engineers",

address = "United States",

}

Zhang, M, Wang, X, Yang, D, Cui, Z & Christensen, MG 2020, Transfer Learning for Identifying Impedance Estimation in Voltage Source Inverters. in 2020 IEEE Energy Conversion Congress and Exposition (ECCE)., 9236090, Institute of Electrical and Electronics Engineers, pp. 6170-6174, 12th Annual IEEE Energy Conversion Congress and Exposition, ECCE 2020, Virtual, Detroit, United States, 11/10/20. https://doi.org/10.1109/ECCE44975.2020.9236090

Transfer Learning for Identifying Impedance Estimation in Voltage Source Inverters. / Zhang, Mengfan; Wang, Xiongfei; Yang, Dongsheng et al.
2020 IEEE Energy Conversion Congress and Exposition (ECCE). Institute of Electrical and Electronics Engineers, 2020. p. 6170-6174 9236090.

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

TY - GEN

T1 - Transfer Learning for Identifying Impedance Estimation in Voltage Source Inverters

AU - Zhang, Mengfan

AU - Wang, Xiongfei

AU - Yang, Dongsheng

AU - Cui, Zihao

AU - Christensen, Mads Grasboll

PY - 2020/10/30

Y1 - 2020/10/30

N2 - The black-box impedance model of the voltage source inverters (VSIs) can be directly identified at the converter terminal without access to its internal control details, which greatly facilitate the converter-grid interactions. However, since the converter is inherently a nonlinear system, the measured converter impedance model will change along with the operating point. As the limited data amount in practical industrial applications, the existing impedance identification method cannot capture this operating point-dependent feature of the impedance model. In this paper, the model-based transfer learning method is employed to generate the operating-point dependent impedance model. This method can significantly reduce the required data amount used in model training so that the machine learning-based method could be applied for the practical industrial application. The comparison results confirm the accuracy of the impedance model obtained by this data-driven impedance identification method.

AB - The black-box impedance model of the voltage source inverters (VSIs) can be directly identified at the converter terminal without access to its internal control details, which greatly facilitate the converter-grid interactions. However, since the converter is inherently a nonlinear system, the measured converter impedance model will change along with the operating point. As the limited data amount in practical industrial applications, the existing impedance identification method cannot capture this operating point-dependent feature of the impedance model. In this paper, the model-based transfer learning method is employed to generate the operating-point dependent impedance model. This method can significantly reduce the required data amount used in model training so that the machine learning-based method could be applied for the practical industrial application. The comparison results confirm the accuracy of the impedance model obtained by this data-driven impedance identification method.

KW - Deep neural network

KW - impedance identification

KW - operating point variation

KW - transfer learning

KW - voltage source inverter

UR - https://www.scopus.com/pages/publications/85097160224

U2 - 10.1109/ECCE44975.2020.9236090

DO - 10.1109/ECCE44975.2020.9236090

M3 - Conference contribution

AN - SCOPUS:85097160224

SP - 6170

EP - 6174

BT - 2020 IEEE Energy Conversion Congress and Exposition (ECCE)

PB - Institute of Electrical and Electronics Engineers

T2 - 12th Annual IEEE Energy Conversion Congress and Exposition, ECCE 2020

Y2 - 11 October 2020 through 15 October 2020

ER -

Transfer Learning for Identifying Impedance Estimation in Voltage Source Inverters

Abstract

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this