Synthetic training data generation for ML-based small-signal stability assessment

Sergio A. Dorado-Rojas; Marcelo De Castro Fernandes; Luigi Vanfretti

doi:10.1109/SmartGridComm47815.2020.9302991

Synthetic training data generation for ML-based small-signal stability assessment

Sergio A. Dorado-Rojas, Marcelo De Castro Fernandes, Luigi Vanfretti

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

6 Scopus citations

Abstract

This article presents a simulation-based massive data generation procedure with applications in training machine learning (ML) solutions to automatically assess the small-signal stability condition of a power system subjected to contingencies. This method of scenario generation for employs a Monte Carlo two-stage sampling procedure to set up a contingency condition while considering the likelihood of a given combination of line outages. The generated data is pre-processed and then used to train several ML models (logistic and softmax regression, support vector machines, k-nearest Neighbors, Naïve Bayes and decision trees), and a deep learning neural network. The performance of the ML algorithms shows the potential to be deployed in efficient real-time solutions to assist power system operators.

Original language	English (US)
Title of host publication	2020 IEEE International Conference on Communications, Control, and Computing Technologies for Smart Grids (SmartGridComm)
Publisher	IEEE
ISBN (Print)	9781728161273
DOIs	https://doi.org/10.1109/SmartGridComm47815.2020.9302991
State	Published - Dec 30 2020
Externally published	Yes

Bibliographical note

KAUST Repository Item: Exported on 2022-07-01
Acknowledgements: This work was funded in part by the New York State Energy Research and Development Authority (NYSERDA) through the Electric Power Transmission and Distribution (EPTD) High Performing Grid Program under agreement number 137951, in part by the Engineering Research Center Program of the National Science Foundation and the Department of Energy under Award EEC-1041877, in part by the CURENT Industry Partnership Program, and in part by the Center of Excellence for NEOM Research at King Abdullah University of Science and Technology.
This publication acknowledges KAUST support, but has no KAUST affiliated authors.

Access to Document

10.1109/SmartGridComm47815.2020.9302991

Cite this

@inproceedings{fca98212480e4d45ac79b5e00384b2d0,

title = "Synthetic training data generation for ML-based small-signal stability assessment",

abstract = "This article presents a simulation-based massive data generation procedure with applications in training machine learning (ML) solutions to automatically assess the small-signal stability condition of a power system subjected to contingencies. This method of scenario generation for employs a Monte Carlo two-stage sampling procedure to set up a contingency condition while considering the likelihood of a given combination of line outages. The generated data is pre-processed and then used to train several ML models (logistic and softmax regression, support vector machines, k-nearest Neighbors, Na{\"i}ve Bayes and decision trees), and a deep learning neural network. The performance of the ML algorithms shows the potential to be deployed in efficient real-time solutions to assist power system operators.",

author = "Dorado-Rojas, {Sergio A.} and {De Castro Fernandes}, Marcelo and Luigi Vanfretti",

note = "KAUST Repository Item: Exported on 2022-07-01 Acknowledgements: This work was funded in part by the New York State Energy Research and Development Authority (NYSERDA) through the Electric Power Transmission and Distribution (EPTD) High Performing Grid Program under agreement number 137951, in part by the Engineering Research Center Program of the National Science Foundation and the Department of Energy under Award EEC-1041877, in part by the CURENT Industry Partnership Program, and in part by the Center of Excellence for NEOM Research at King Abdullah University of Science and Technology. This publication acknowledges KAUST support, but has no KAUST affiliated authors.",

year = "2020",

month = dec,

day = "30",

doi = "10.1109/SmartGridComm47815.2020.9302991",

language = "English (US)",

isbn = "9781728161273",

booktitle = "2020 IEEE International Conference on Communications, Control, and Computing Technologies for Smart Grids (SmartGridComm)",

publisher = "IEEE",

}

Synthetic training data generation for ML-based small-signal stability assessment. / Dorado-Rojas, Sergio A.; De Castro Fernandes, Marcelo; Vanfretti, Luigi.
2020 IEEE International Conference on Communications, Control, and Computing Technologies for Smart Grids (SmartGridComm). IEEE, 2020.

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

TY - GEN

T1 - Synthetic training data generation for ML-based small-signal stability assessment

AU - Dorado-Rojas, Sergio A.

AU - De Castro Fernandes, Marcelo

AU - Vanfretti, Luigi

N1 - KAUST Repository Item: Exported on 2022-07-01 Acknowledgements: This work was funded in part by the New York State Energy Research and Development Authority (NYSERDA) through the Electric Power Transmission and Distribution (EPTD) High Performing Grid Program under agreement number 137951, in part by the Engineering Research Center Program of the National Science Foundation and the Department of Energy under Award EEC-1041877, in part by the CURENT Industry Partnership Program, and in part by the Center of Excellence for NEOM Research at King Abdullah University of Science and Technology. This publication acknowledges KAUST support, but has no KAUST affiliated authors.

PY - 2020/12/30

Y1 - 2020/12/30

N2 - This article presents a simulation-based massive data generation procedure with applications in training machine learning (ML) solutions to automatically assess the small-signal stability condition of a power system subjected to contingencies. This method of scenario generation for employs a Monte Carlo two-stage sampling procedure to set up a contingency condition while considering the likelihood of a given combination of line outages. The generated data is pre-processed and then used to train several ML models (logistic and softmax regression, support vector machines, k-nearest Neighbors, Naïve Bayes and decision trees), and a deep learning neural network. The performance of the ML algorithms shows the potential to be deployed in efficient real-time solutions to assist power system operators.

AB - This article presents a simulation-based massive data generation procedure with applications in training machine learning (ML) solutions to automatically assess the small-signal stability condition of a power system subjected to contingencies. This method of scenario generation for employs a Monte Carlo two-stage sampling procedure to set up a contingency condition while considering the likelihood of a given combination of line outages. The generated data is pre-processed and then used to train several ML models (logistic and softmax regression, support vector machines, k-nearest Neighbors, Naïve Bayes and decision trees), and a deep learning neural network. The performance of the ML algorithms shows the potential to be deployed in efficient real-time solutions to assist power system operators.

UR - http://hdl.handle.net/10754/679539

UR - https://ieeexplore.ieee.org/document/9302991/

UR - http://www.scopus.com/inward/record.url?scp=85099467424&partnerID=8YFLogxK

U2 - 10.1109/SmartGridComm47815.2020.9302991

DO - 10.1109/SmartGridComm47815.2020.9302991

M3 - Conference contribution

SN - 9781728161273

BT - 2020 IEEE International Conference on Communications, Control, and Computing Technologies for Smart Grids (SmartGridComm)

PB - IEEE

ER -

Synthetic training data generation for ML-based small-signal stability assessment

Abstract

Bibliographical note

Access to Document

Other files and links

Fingerprint

Cite this