Article ID | Journal | Published Year | Pages | File Type |
---|---|---|---|---|
388879 | Expert Systems with Applications | 2008 | 7 Pages |
Abstract
This paper proposes a methodology for online voltage stability monitoring using artificial neural network (ANN) and a regression-based method of selecting features for training the ANN. Separate ANNs are used for different contingencies. Important features for the ANN are selected by using the sensitivities of the voltage stability margin with respect to the inputs. The sensitivities are computed by using the regression models, which overcomes many limitations of the conventional methods of computing sensitivities. The implementation of the feature selection scheme enhances the overall design of the neural network. The proposed scheme is applied on the New England 39-bus power system model.
Related Topics
Physical Sciences and Engineering
Computer Science
Artificial Intelligence
Authors
S. Chakrabarti,