Parameter optimization of PSS based on estimated hessian matrix from trajectory sensitivities

Seung Mook Baek, Jung Wook Park, Ganesh K. Venayagamoorthy

Research output: Chapter in Book/Report/Conference proceedingConference contribution

4 Citations (Scopus)

Abstract

This paper describes the optimal tuning for the output limits of the power system stabilizer (PSS), which can improve the system damping performance immediately following a large disturbance. The non-smooth nonlinear parameters such as the saturation limits of the PSS cannot be tuned by the conventional methods based on linear approaches. To implement the systematic optimal tuning for the output limits of the PSS, a feedforward neural network (FFNN) is applied to the hybrid system model based on the differential-algebraic- impulsive-switched (DAIS) structure. The FFNN is firstly designed to identify the trajectory sensitivities obtained from the DAIS structure. Thereafter, it estimates the second-order derivatives of an objective function J, which is used during iterations of optimization process. The performance of the optimal output limits tuned by the proposed method is evaluated by applying a large disturbance to a power system.

Original languageEnglish
Title of host publicationThe 2007 International Joint Conference on Neural Networks, IJCNN 2007 Conference Proceedings
Pages979-984
Number of pages6
DOIs
Publication statusPublished - 2007 Dec 1
Event2007 International Joint Conference on Neural Networks, IJCNN 2007 - Orlando, FL, United States
Duration: 2007 Aug 122007 Aug 17

Other

Other2007 International Joint Conference on Neural Networks, IJCNN 2007
CountryUnited States
CityOrlando, FL
Period07/8/1207/8/17

Fingerprint

Feedforward neural networks
Tuning
Trajectories
Hybrid systems
Damping
Derivatives

All Science Journal Classification (ASJC) codes

  • Software

Cite this

Baek, S. M., Park, J. W., & Venayagamoorthy, G. K. (2007). Parameter optimization of PSS based on estimated hessian matrix from trajectory sensitivities. In The 2007 International Joint Conference on Neural Networks, IJCNN 2007 Conference Proceedings (pp. 979-984). [4371091] https://doi.org/10.1109/IJCNN.2007.4371091
Baek, Seung Mook ; Park, Jung Wook ; Venayagamoorthy, Ganesh K. / Parameter optimization of PSS based on estimated hessian matrix from trajectory sensitivities. The 2007 International Joint Conference on Neural Networks, IJCNN 2007 Conference Proceedings. 2007. pp. 979-984
@inproceedings{3fb5c87ad19f4d9882161831e53c59fb,
title = "Parameter optimization of PSS based on estimated hessian matrix from trajectory sensitivities",
abstract = "This paper describes the optimal tuning for the output limits of the power system stabilizer (PSS), which can improve the system damping performance immediately following a large disturbance. The non-smooth nonlinear parameters such as the saturation limits of the PSS cannot be tuned by the conventional methods based on linear approaches. To implement the systematic optimal tuning for the output limits of the PSS, a feedforward neural network (FFNN) is applied to the hybrid system model based on the differential-algebraic- impulsive-switched (DAIS) structure. The FFNN is firstly designed to identify the trajectory sensitivities obtained from the DAIS structure. Thereafter, it estimates the second-order derivatives of an objective function J, which is used during iterations of optimization process. The performance of the optimal output limits tuned by the proposed method is evaluated by applying a large disturbance to a power system.",
author = "Baek, {Seung Mook} and Park, {Jung Wook} and Venayagamoorthy, {Ganesh K.}",
year = "2007",
month = "12",
day = "1",
doi = "10.1109/IJCNN.2007.4371091",
language = "English",
isbn = "142441380X",
pages = "979--984",
booktitle = "The 2007 International Joint Conference on Neural Networks, IJCNN 2007 Conference Proceedings",

}

Baek, SM, Park, JW & Venayagamoorthy, GK 2007, Parameter optimization of PSS based on estimated hessian matrix from trajectory sensitivities. in The 2007 International Joint Conference on Neural Networks, IJCNN 2007 Conference Proceedings., 4371091, pp. 979-984, 2007 International Joint Conference on Neural Networks, IJCNN 2007, Orlando, FL, United States, 07/8/12. https://doi.org/10.1109/IJCNN.2007.4371091

Parameter optimization of PSS based on estimated hessian matrix from trajectory sensitivities. / Baek, Seung Mook; Park, Jung Wook; Venayagamoorthy, Ganesh K.

The 2007 International Joint Conference on Neural Networks, IJCNN 2007 Conference Proceedings. 2007. p. 979-984 4371091.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Parameter optimization of PSS based on estimated hessian matrix from trajectory sensitivities

AU - Baek, Seung Mook

AU - Park, Jung Wook

AU - Venayagamoorthy, Ganesh K.

PY - 2007/12/1

Y1 - 2007/12/1

N2 - This paper describes the optimal tuning for the output limits of the power system stabilizer (PSS), which can improve the system damping performance immediately following a large disturbance. The non-smooth nonlinear parameters such as the saturation limits of the PSS cannot be tuned by the conventional methods based on linear approaches. To implement the systematic optimal tuning for the output limits of the PSS, a feedforward neural network (FFNN) is applied to the hybrid system model based on the differential-algebraic- impulsive-switched (DAIS) structure. The FFNN is firstly designed to identify the trajectory sensitivities obtained from the DAIS structure. Thereafter, it estimates the second-order derivatives of an objective function J, which is used during iterations of optimization process. The performance of the optimal output limits tuned by the proposed method is evaluated by applying a large disturbance to a power system.

AB - This paper describes the optimal tuning for the output limits of the power system stabilizer (PSS), which can improve the system damping performance immediately following a large disturbance. The non-smooth nonlinear parameters such as the saturation limits of the PSS cannot be tuned by the conventional methods based on linear approaches. To implement the systematic optimal tuning for the output limits of the PSS, a feedforward neural network (FFNN) is applied to the hybrid system model based on the differential-algebraic- impulsive-switched (DAIS) structure. The FFNN is firstly designed to identify the trajectory sensitivities obtained from the DAIS structure. Thereafter, it estimates the second-order derivatives of an objective function J, which is used during iterations of optimization process. The performance of the optimal output limits tuned by the proposed method is evaluated by applying a large disturbance to a power system.

UR - http://www.scopus.com/inward/record.url?scp=51749089782&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=51749089782&partnerID=8YFLogxK

U2 - 10.1109/IJCNN.2007.4371091

DO - 10.1109/IJCNN.2007.4371091

M3 - Conference contribution

SN - 142441380X

SN - 9781424413805

SP - 979

EP - 984

BT - The 2007 International Joint Conference on Neural Networks, IJCNN 2007 Conference Proceedings

ER -

Baek SM, Park JW, Venayagamoorthy GK. Parameter optimization of PSS based on estimated hessian matrix from trajectory sensitivities. In The 2007 International Joint Conference on Neural Networks, IJCNN 2007 Conference Proceedings. 2007. p. 979-984. 4371091 https://doi.org/10.1109/IJCNN.2007.4371091