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
Event2007 International Joint Conference on Neural Networks, IJCNN 2007 - Orlando, FL, United States
Duration: 2007 Aug 122007 Aug 17

Publication series

NameIEEE International Conference on Neural Networks - Conference Proceedings
ISSN (Print)1098-7576

Other

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

All Science Journal Classification (ASJC) codes

  • Software

Fingerprint Dive into the research topics of 'Parameter optimization of PSS based on estimated hessian matrix from trajectory sensitivities'. Together they form a unique fingerprint.

Cite this