Power system control with an embedded neural network in hybrid system modeling

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

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

Abstract

The output limits of the power system stabilizer (PSS) can improve the system damping performance immediately following a large disturbance. Due to non-smooth nonlinearities from the saturation limits, these values cannot be determined by the conventional tuning methods based on linear analysis. Only ad hoc tuning procedures can been used. A feedforward neural network (FFNN) (with a structure of multilayer perceptron neural network) is applied to identify the dynamics of an objective function formed by the states, and thereafter to compute the gradients required in the nonlinear parameter optimization. Moreover, its derivative information is used to replace that obtained from the trajectory sensitivities based on the hybrid system model with the differential-algebraic-impulsive-switched (DAIS) structure. The optimal output limits of the PSS tuned by the proposed method are evaluated by timedomain simulation in both a single machine infinite bus system (SMIB) and a multi-machine power system (MMPS).

Original languageEnglish
Title of host publicationConference Record of the 2006 IEEE Industry Applications Conference - Forty-First IAS Annual Meeting
Pages650-657
Number of pages8
DOIs
Publication statusPublished - 2006 Dec 1
Event2006 IEEE Industry Applications Conference - Forty-First IAS Annual Meeting - Tampa, FL, United States
Duration: 2006 Oct 82006 Oct 12

Publication series

NameConference Record - IAS Annual Meeting (IEEE Industry Applications Society)
Volume2
ISSN (Print)0197-2618

Other

Other2006 IEEE Industry Applications Conference - Forty-First IAS Annual Meeting
CountryUnited States
CityTampa, FL
Period06/10/806/10/12

Fingerprint

Hybrid systems
Tuning
Neural networks
Control systems
Feedforward neural networks
Multilayer neural networks
Damping
Trajectories
Derivatives

All Science Journal Classification (ASJC) codes

  • Control and Systems Engineering
  • Industrial and Manufacturing Engineering
  • Electrical and Electronic Engineering

Cite this

Baek, S. M., Park, J. W., & Venayagamoorthy, G. K. (2006). Power system control with an embedded neural network in hybrid system modeling. In Conference Record of the 2006 IEEE Industry Applications Conference - Forty-First IAS Annual Meeting (pp. 650-657). [4025281] (Conference Record - IAS Annual Meeting (IEEE Industry Applications Society); Vol. 2). https://doi.org/10.1109/IAS.2006.256595
Baek, Seung Mook ; Park, Jung Wook ; Venayagamoorthy, Ganesh K. / Power system control with an embedded neural network in hybrid system modeling. Conference Record of the 2006 IEEE Industry Applications Conference - Forty-First IAS Annual Meeting. 2006. pp. 650-657 (Conference Record - IAS Annual Meeting (IEEE Industry Applications Society)).
@inproceedings{2167e7b2de7d4c2c816f318f4a2912dd,
title = "Power system control with an embedded neural network in hybrid system modeling",
abstract = "The output limits of the power system stabilizer (PSS) can improve the system damping performance immediately following a large disturbance. Due to non-smooth nonlinearities from the saturation limits, these values cannot be determined by the conventional tuning methods based on linear analysis. Only ad hoc tuning procedures can been used. A feedforward neural network (FFNN) (with a structure of multilayer perceptron neural network) is applied to identify the dynamics of an objective function formed by the states, and thereafter to compute the gradients required in the nonlinear parameter optimization. Moreover, its derivative information is used to replace that obtained from the trajectory sensitivities based on the hybrid system model with the differential-algebraic-impulsive-switched (DAIS) structure. The optimal output limits of the PSS tuned by the proposed method are evaluated by timedomain simulation in both a single machine infinite bus system (SMIB) and a multi-machine power system (MMPS).",
author = "Baek, {Seung Mook} and Park, {Jung Wook} and Venayagamoorthy, {Ganesh K.}",
year = "2006",
month = "12",
day = "1",
doi = "10.1109/IAS.2006.256595",
language = "English",
isbn = "1424403642",
series = "Conference Record - IAS Annual Meeting (IEEE Industry Applications Society)",
pages = "650--657",
booktitle = "Conference Record of the 2006 IEEE Industry Applications Conference - Forty-First IAS Annual Meeting",

}

Baek, SM, Park, JW & Venayagamoorthy, GK 2006, Power system control with an embedded neural network in hybrid system modeling. in Conference Record of the 2006 IEEE Industry Applications Conference - Forty-First IAS Annual Meeting., 4025281, Conference Record - IAS Annual Meeting (IEEE Industry Applications Society), vol. 2, pp. 650-657, 2006 IEEE Industry Applications Conference - Forty-First IAS Annual Meeting, Tampa, FL, United States, 06/10/8. https://doi.org/10.1109/IAS.2006.256595

Power system control with an embedded neural network in hybrid system modeling. / Baek, Seung Mook; Park, Jung Wook; Venayagamoorthy, Ganesh K.

Conference Record of the 2006 IEEE Industry Applications Conference - Forty-First IAS Annual Meeting. 2006. p. 650-657 4025281 (Conference Record - IAS Annual Meeting (IEEE Industry Applications Society); Vol. 2).

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

TY - GEN

T1 - Power system control with an embedded neural network in hybrid system modeling

AU - Baek, Seung Mook

AU - Park, Jung Wook

AU - Venayagamoorthy, Ganesh K.

PY - 2006/12/1

Y1 - 2006/12/1

N2 - The output limits of the power system stabilizer (PSS) can improve the system damping performance immediately following a large disturbance. Due to non-smooth nonlinearities from the saturation limits, these values cannot be determined by the conventional tuning methods based on linear analysis. Only ad hoc tuning procedures can been used. A feedforward neural network (FFNN) (with a structure of multilayer perceptron neural network) is applied to identify the dynamics of an objective function formed by the states, and thereafter to compute the gradients required in the nonlinear parameter optimization. Moreover, its derivative information is used to replace that obtained from the trajectory sensitivities based on the hybrid system model with the differential-algebraic-impulsive-switched (DAIS) structure. The optimal output limits of the PSS tuned by the proposed method are evaluated by timedomain simulation in both a single machine infinite bus system (SMIB) and a multi-machine power system (MMPS).

AB - The output limits of the power system stabilizer (PSS) can improve the system damping performance immediately following a large disturbance. Due to non-smooth nonlinearities from the saturation limits, these values cannot be determined by the conventional tuning methods based on linear analysis. Only ad hoc tuning procedures can been used. A feedforward neural network (FFNN) (with a structure of multilayer perceptron neural network) is applied to identify the dynamics of an objective function formed by the states, and thereafter to compute the gradients required in the nonlinear parameter optimization. Moreover, its derivative information is used to replace that obtained from the trajectory sensitivities based on the hybrid system model with the differential-algebraic-impulsive-switched (DAIS) structure. The optimal output limits of the PSS tuned by the proposed method are evaluated by timedomain simulation in both a single machine infinite bus system (SMIB) and a multi-machine power system (MMPS).

UR - http://www.scopus.com/inward/record.url?scp=34948885619&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=34948885619&partnerID=8YFLogxK

U2 - 10.1109/IAS.2006.256595

DO - 10.1109/IAS.2006.256595

M3 - Conference contribution

SN - 1424403642

SN - 9781424403646

T3 - Conference Record - IAS Annual Meeting (IEEE Industry Applications Society)

SP - 650

EP - 657

BT - Conference Record of the 2006 IEEE Industry Applications Conference - Forty-First IAS Annual Meeting

ER -

Baek SM, Park JW, Venayagamoorthy GK. Power system control with an embedded neural network in hybrid system modeling. In Conference Record of the 2006 IEEE Industry Applications Conference - Forty-First IAS Annual Meeting. 2006. p. 650-657. 4025281. (Conference Record - IAS Annual Meeting (IEEE Industry Applications Society)). https://doi.org/10.1109/IAS.2006.256595