DocumentCode :
2989343
Title :
Input feature selection for real-time transient stability assessment for artificial neural network (ANN) using ANN sensitivity analysis
Author :
Bahbah, Amr G. ; Girgis, Adly A.
Author_Institution :
Dept. of Electr. & Comput. Eng., Clemson Univ., SC, USA
fYear :
1999
fDate :
36342
Firstpage :
295
Lastpage :
300
Abstract :
This paper presents a method for the selection of the input parameters, and their ranking for feedforward artificial neural networks (FF-ANN) applications in transient stability assessment. The method utilizes feedforward artificial neural networks to estimate the sensitivity of the output to all inputs. An evaluation of most of the common inputs used by the researchers is made. Sensitivity analysis using ANN is performed on key parameters to obtain the optimal ranking of the ANN input features. The critical clearing time (CCT) is used to assess the transient stability of the system. The proposed method is applied to a simple power system to illustrate the concept. The preliminary results show that the proposed sensitivity factors are converging to stable values
Keywords :
feedforward neural nets; power system analysis computing; power system transient stability; real-time systems; sensitivity analysis; ANN sensitivity analysis; artificial neural network; critical clearing time; feedforward artificial neural networks; input feature selection; input parameters; optimal ranking; real-time transient stability assessment; sensitivity estimation; transient stability assessment; Artificial neural networks; Neural networks; Power system dynamics; Power system measurements; Power system modeling; Power system relaying; Power system security; Power system stability; Power system transients; Sensitivity analysis;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Power Industry Computer Applications, 1999. PICA '99. Proceedings of the 21st 1999 IEEE International Conference
Conference_Location :
Santa Clara, CA
Print_ISBN :
0-7803-5478-8
Type :
conf
DOI :
10.1109/PICA.1999.779510
Filename :
779510
Link To Document :
بازگشت