Power system on-line transient stability prediction by margin indices and random forests

Yuchuan Chen; Seyed Mahdi Mazhari; C. Y. Chung; Sherif O. Faried; Bingzhi Wang; Bo Hu

doi:10.1109/EPEC47565.2019.9074804

Power system on-line transient stability prediction by margin indices and random forests

Yuchuan Chen
, Seyed Mahdi Mazhari
, C. Y. Chung
, Sherif O. Faried
, Bingzhi Wang
, Bo Hu

Research output: Chapter in book / Conference proceeding › Conference article published in proceeding or book › Academic research › peer-review

4 Citations (Scopus)

Abstract

This paper addresses a novel approach for on-line transient stability prediction for power systems. In the proposed framework, the feasible instability classes (ICs) of a power system is first identified by off-line simulation considering the uncertainties of load and all potential contingencies. Accordingly, after contingencies, the stability margins (SMs) for each possible IC can be rapidly calculated using direct methods. These SMs are chosen as features for the prediction models trained by random forests, which further demonstrate a better prediction performance compared to other features used in previous machine learning based method. The proposed approach is validated on two IEEE test systems and compared to existing methods.

Original language	English
Title of host publication	2019 IEEE Electrical Power and Energy Conference, EPEC 2019
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	9781728134062
DOIs	https://doi.org/10.1109/EPEC47565.2019.9074804
Publication status	Published - Oct 2019
Externally published	Yes
Event	2019 IEEE Electrical Power and Energy Conference, EPEC 2019 - Montreal, Canada Duration: 16 Oct 2019 → 18 Oct 2019

Publication series

Name	2019 IEEE Electrical Power and Energy Conference, EPEC 2019

Conference

Conference	2019 IEEE Electrical Power and Energy Conference, EPEC 2019
Country/Territory	Canada
City	Montreal
Period	16/10/19 → 18/10/19

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 7 Affordable and Clean Energy

Keywords

Direct methods
feature engineering
machine learning
phasor measurement units
random forests
transient stability prediction

ASJC Scopus subject areas

Renewable Energy, Sustainability and the Environment
Electrical and Electronic Engineering
Artificial Intelligence
Energy Engineering and Power Technology

More information

10.1109/EPEC47565.2019.9074804

Cite this

Chen, Y., Mazhari, S. M., Chung, C. Y., Faried, S. O., Wang, B., & Hu, B. (2019). Power system on-line transient stability prediction by margin indices and random forests. In 2019 IEEE Electrical Power and Energy Conference, EPEC 2019 Article 9074804 (2019 IEEE Electrical Power and Energy Conference, EPEC 2019). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/EPEC47565.2019.9074804

@inproceedings{f9535bdcb8f84c6a8ccb1c875162fb1d,

title = "Power system on-line transient stability prediction by margin indices and random forests",

abstract = "This paper addresses a novel approach for on-line transient stability prediction for power systems. In the proposed framework, the feasible instability classes (ICs) of a power system is first identified by off-line simulation considering the uncertainties of load and all potential contingencies. Accordingly, after contingencies, the stability margins (SMs) for each possible IC can be rapidly calculated using direct methods. These SMs are chosen as features for the prediction models trained by random forests, which further demonstrate a better prediction performance compared to other features used in previous machine learning based method. The proposed approach is validated on two IEEE test systems and compared to existing methods.",

keywords = "Direct methods, feature engineering, machine learning, phasor measurement units, random forests, transient stability prediction",

author = "Yuchuan Chen and Mazhari, \{Seyed Mahdi\} and Chung, \{C. Y.\} and Faried, \{Sherif O.\} and Bingzhi Wang and Bo Hu",

note = "Publisher Copyright: {\textcopyright} 2019 IEEE.; 2019 IEEE Electrical Power and Energy Conference, EPEC 2019 ; Conference date: 16-10-2019 Through 18-10-2019",

year = "2019",

month = oct,

doi = "10.1109/EPEC47565.2019.9074804",

language = "English",

series = "2019 IEEE Electrical Power and Energy Conference, EPEC 2019",

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

booktitle = "2019 IEEE Electrical Power and Energy Conference, EPEC 2019",

}

Chen, Y, Mazhari, SM, Chung, CY, Faried, SO, Wang, B & Hu, B 2019, Power system on-line transient stability prediction by margin indices and random forests. in 2019 IEEE Electrical Power and Energy Conference, EPEC 2019., 9074804, 2019 IEEE Electrical Power and Energy Conference, EPEC 2019, Institute of Electrical and Electronics Engineers Inc., 2019 IEEE Electrical Power and Energy Conference, EPEC 2019, Montreal, Canada, 16/10/19. https://doi.org/10.1109/EPEC47565.2019.9074804

Power system on-line transient stability prediction by margin indices and random forests. / Chen, Yuchuan; Mazhari, Seyed Mahdi; Chung, C. Y. et al.
2019 IEEE Electrical Power and Energy Conference, EPEC 2019. Institute of Electrical and Electronics Engineers Inc., 2019. 9074804 (2019 IEEE Electrical Power and Energy Conference, EPEC 2019).

Research output: Chapter in book / Conference proceeding › Conference article published in proceeding or book › Academic research › peer-review

TY - GEN

T1 - Power system on-line transient stability prediction by margin indices and random forests

AU - Chen, Yuchuan

AU - Mazhari, Seyed Mahdi

AU - Chung, C. Y.

AU - Faried, Sherif O.

AU - Wang, Bingzhi

AU - Hu, Bo

PY - 2019/10

Y1 - 2019/10

N2 - This paper addresses a novel approach for on-line transient stability prediction for power systems. In the proposed framework, the feasible instability classes (ICs) of a power system is first identified by off-line simulation considering the uncertainties of load and all potential contingencies. Accordingly, after contingencies, the stability margins (SMs) for each possible IC can be rapidly calculated using direct methods. These SMs are chosen as features for the prediction models trained by random forests, which further demonstrate a better prediction performance compared to other features used in previous machine learning based method. The proposed approach is validated on two IEEE test systems and compared to existing methods.

AB - This paper addresses a novel approach for on-line transient stability prediction for power systems. In the proposed framework, the feasible instability classes (ICs) of a power system is first identified by off-line simulation considering the uncertainties of load and all potential contingencies. Accordingly, after contingencies, the stability margins (SMs) for each possible IC can be rapidly calculated using direct methods. These SMs are chosen as features for the prediction models trained by random forests, which further demonstrate a better prediction performance compared to other features used in previous machine learning based method. The proposed approach is validated on two IEEE test systems and compared to existing methods.

KW - Direct methods

KW - feature engineering

KW - machine learning

KW - phasor measurement units

KW - random forests

KW - transient stability prediction

UR - https://www.scopus.com/pages/publications/85084639171

U2 - 10.1109/EPEC47565.2019.9074804

DO - 10.1109/EPEC47565.2019.9074804

M3 - Conference article published in proceeding or book

AN - SCOPUS:85084639171

T3 - 2019 IEEE Electrical Power and Energy Conference, EPEC 2019

BT - 2019 IEEE Electrical Power and Energy Conference, EPEC 2019

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2019 IEEE Electrical Power and Energy Conference, EPEC 2019

Y2 - 16 October 2019 through 18 October 2019

ER -

Chen Y, Mazhari SM, Chung CY, Faried SO, Wang B, Hu B. Power system on-line transient stability prediction by margin indices and random forests. In 2019 IEEE Electrical Power and Energy Conference, EPEC 2019. Institute of Electrical and Electronics Engineers Inc. 2019. 9074804. (2019 IEEE Electrical Power and Energy Conference, EPEC 2019). doi: 10.1109/EPEC47565.2019.9074804

Power system on-line transient stability prediction by margin indices and random forests

Abstract

Publication series

Conference

UN SDGs

Keywords

ASJC Scopus subject areas

More information

Other files and links

Fingerprint

Cite this