Learning Based Capacitor Voltage Ripple Reduction of Modular Multilevel Converters under Unbalanced Grid Conditions with Different Power Factors

Songda Wang; Tomislav Dragicevic; Remus Teodorescu

doi:10.1109/PEDG48541.2020.9244470

Learning Based Capacitor Voltage Ripple Reduction of Modular Multilevel Converters under Unbalanced Grid Conditions with Different Power Factors

Songda Wang, Tomislav Dragicevic, Remus Teodorescu

Aalborg University

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

Abstract

A fast and non-parameter-dependent grid-current-control method to ride through dangerous unbalanced gird condition is proposed in this paper. The grid-current references are calculated from an artificial intelligence (AI) surrogate model in order to keep the capacitor voltage at a safe level under a two phases short circuit to ground condition. And also, the circulating current reference are determined when the power factor is different when the grid fault is not serious. This machine learning network represents the relation between grid-current references and submodule capacitor voltages. The results show that this method prevents capacitor-overvoltage trips under completely short-circuited grid.

Original language	English
Title of host publication	Proceedings of 2020 IEEE 11^th International Symposium on Power Electronics for Distributed Generation Systems
Publisher	IEEE
Publication date	2020
Pages	531-535
ISBN (Print)	9781728169903
DOIs	https://doi.org/10.1109/PEDG48541.2020.9244470
Publication status	Published - 2020
Event	2020 IEEE 11th International Symposium on Power Electronics for Distributed Generation Systems - Virtual event, Dubrovnik, Croatia Duration: 28 Sept 2020 → 1 Oct 2020 https://ieeexplore.ieee.org/xpl/conhome/9244275/proceeding

Conference

Conference	2020 IEEE 11th International Symposium on Power Electronics for Distributed Generation Systems
Location	Virtual event
Country/Territory	Croatia
City	Dubrovnik
Period	28/09/2020 → 01/10/2020
Internet address	https://ieeexplore.ieee.org/xpl/conhome/9244275/proceeding

Keywords

Modular Multilevel Converters
Submodule capacitor voltage, machine learning
Grid current control

Access to Document

10.1109/PEDG48541.2020.9244470

OpenUrl availability

Full text

Cite this

Wang, S., Dragicevic, T., & Teodorescu, R. (2020). Learning Based Capacitor Voltage Ripple Reduction of Modular Multilevel Converters under Unbalanced Grid Conditions with Different Power Factors. In Proceedings of 2020 IEEE 11^th International Symposium on Power Electronics for Distributed Generation Systems (pp. 531-535). IEEE. https://doi.org/10.1109/PEDG48541.2020.9244470

@inproceedings{c825d0f586ee48eab7e0fbdf9ca04552,

title = "Learning Based Capacitor Voltage Ripple Reduction of Modular Multilevel Converters under Unbalanced Grid Conditions with Different Power Factors",

abstract = "A fast and non-parameter-dependent grid-current-control method to ride through dangerous unbalanced gird condition is proposed in this paper. The grid-current references are calculated from an artificial intelligence (AI) surrogate model in order to keep the capacitor voltage at a safe level under a two phases short circuit to ground condition. And also, the circulating current reference are determined when the power factor is different when the grid fault is not serious. This machine learning network represents the relation between grid-current references and submodule capacitor voltages. The results show that this method prevents capacitor-overvoltage trips under completely short-circuited grid.",

keywords = "Modular Multilevel Converters, Submodule capacitor voltage, machine learning, Grid current control",

author = "Songda Wang and Tomislav Dragicevic and Remus Teodorescu",

year = "2020",

doi = "10.1109/PEDG48541.2020.9244470",

language = "English",

isbn = "9781728169903 ",

pages = "531--535",

booktitle = "Proceedings of 2020 IEEE 11th International Symposium on Power Electronics for Distributed Generation Systems",

publisher = "IEEE",

address = "United States",

note = "2020 IEEE 11th International Symposium on Power Electronics for Distributed Generation Systems, PEDG 2020 ; Conference date: 28-09-2020 Through 01-10-2020",

url = "https://ieeexplore.ieee.org/xpl/conhome/9244275/proceeding",

}

Wang, S, Dragicevic, T & Teodorescu, R 2020, Learning Based Capacitor Voltage Ripple Reduction of Modular Multilevel Converters under Unbalanced Grid Conditions with Different Power Factors. in Proceedings of 2020 IEEE 11^th International Symposium on Power Electronics for Distributed Generation Systems. IEEE, pp. 531-535, 2020 IEEE 11th International Symposium on Power Electronics for Distributed Generation Systems, Dubrovnik, Croatia, 28/09/2020. https://doi.org/10.1109/PEDG48541.2020.9244470

Learning Based Capacitor Voltage Ripple Reduction of Modular Multilevel Converters under Unbalanced Grid Conditions with Different Power Factors. / Wang, Songda; Dragicevic, Tomislav; Teodorescu, Remus.
Proceedings of 2020 IEEE 11^th International Symposium on Power Electronics for Distributed Generation Systems. IEEE, 2020. p. 531-535.

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

TY - GEN

T1 - Learning Based Capacitor Voltage Ripple Reduction of Modular Multilevel Converters under Unbalanced Grid Conditions with Different Power Factors

AU - Wang, Songda

AU - Dragicevic, Tomislav

AU - Teodorescu, Remus

PY - 2020

Y1 - 2020

N2 - A fast and non-parameter-dependent grid-current-control method to ride through dangerous unbalanced gird condition is proposed in this paper. The grid-current references are calculated from an artificial intelligence (AI) surrogate model in order to keep the capacitor voltage at a safe level under a two phases short circuit to ground condition. And also, the circulating current reference are determined when the power factor is different when the grid fault is not serious. This machine learning network represents the relation between grid-current references and submodule capacitor voltages. The results show that this method prevents capacitor-overvoltage trips under completely short-circuited grid.

AB - A fast and non-parameter-dependent grid-current-control method to ride through dangerous unbalanced gird condition is proposed in this paper. The grid-current references are calculated from an artificial intelligence (AI) surrogate model in order to keep the capacitor voltage at a safe level under a two phases short circuit to ground condition. And also, the circulating current reference are determined when the power factor is different when the grid fault is not serious. This machine learning network represents the relation between grid-current references and submodule capacitor voltages. The results show that this method prevents capacitor-overvoltage trips under completely short-circuited grid.

KW - Modular Multilevel Converters

KW - Submodule capacitor voltage, machine learning

KW - Grid current control

U2 - 10.1109/PEDG48541.2020.9244470

DO - 10.1109/PEDG48541.2020.9244470

M3 - Article in proceedings

SN - 9781728169903

SP - 531

EP - 535

BT - Proceedings of 2020 IEEE 11th International Symposium on Power Electronics for Distributed Generation Systems

PB - IEEE

T2 - 2020 IEEE 11th International Symposium on Power Electronics for Distributed Generation Systems

Y2 - 28 September 2020 through 1 October 2020

ER -

Learning Based Capacitor Voltage Ripple Reduction of Modular Multilevel Converters under Unbalanced Grid Conditions with Different Power Factors

Abstract

Conference

Keywords

Access to Document

OpenUrl availability

Fingerprint

Cite this