A hybrid artificial neural network for voltage security evaluation in a power system

Авторы: Zhukov A., Panasetsky D.A., Tomin N., Sidorov D., Spirayev V.
Сборник: IYCE 2015 - Proceedings: 2015 5th International Youth Conference on Energy
Год издания: 2015
Первая страница: 7180828
Последняя страница: 7180828
DOI: 10.1109/IYCE.2015.7180828
Аннотация: 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.
Добавил в систему: Сидоров Денис Николаевич

	ИСТИНА	Войти в систему Регистрация
	ИСТИНА ИНХС РАН
	Главная Поиск Статистика О проекте Помощь

ИСТИНА