A hybrid artificial neural network for voltage security evaluation in a power system
A majority of recent large-scale blackouts have been the consequence of instabilities characterized by sudden voltage collapse phenomena. This paper presents a method for voltage instability monitoring in a power system with a hybrid artificial neural network which consist of a multilayer perceptron and the Kohonen neural network. The proposed method has a couple of the following functions: the Kohonen network is used to classify the system operating state; the Kohonen output patterns are used as inputs to train of a multilayer perceptron for identification of alarm states that are dangerous for the system security. The approach is targeting a blackout prevention scheme; given that the blackout signal is captured before it can collapse the power system. The proposed method is realized in R and demonstrated the modified IEEE One Area RTS-96 power system. © 2015 IEEE.
Библиографическая ссылка Zhukov A., Tomin N., Sidorov D., Panasetsky D., Spirayev V. A hybrid artificial neural network for voltage security evaluation in a power system // IYCE 2015 - Proceedings: 2015 5th International Youth Conference on Energy. 2015. 1 p. ISBN (print): 9781467371. DOI: 10.1109/IYCE.2015.7180828
Проиндексировано: WOS
SCOPUS
