This paper presents a neural-network based method for evaluating on-line power system voltage stability. Starting with an appropriate linearized model of the system, the proximity of the power system to the voltage instability is quantified by using a suitable index. Then, a three-layer feedforward neural network is trained to learn the underlying features of the voltage stability phenomenon. Once trained, the neural network provides the above mentioned voltage stability index as output to a pre-defined set of input variables that are known to influence directly the voltage stability conditions of the load area. The. effectiveness of the proposed approach has been tested on the 39-busbar New England test system.

Towards a neural network based voltage stability assessment / Cory, B. J.; Knight, U. G.; Gabellone, L.; Trovato, M.. - In: ENGINEERING INTELLIGENT SYSTEMS FOR ELECTRICAL ENGINEERING AND COMMUNICATIONS. - ISSN 1472-8915. - STAMPA. - 4:1(1996), pp. 25-31.

Towards a neural network based voltage stability assessment

Trovato, M.
1996-01-01

Abstract

This paper presents a neural-network based method for evaluating on-line power system voltage stability. Starting with an appropriate linearized model of the system, the proximity of the power system to the voltage instability is quantified by using a suitable index. Then, a three-layer feedforward neural network is trained to learn the underlying features of the voltage stability phenomenon. Once trained, the neural network provides the above mentioned voltage stability index as output to a pre-defined set of input variables that are known to influence directly the voltage stability conditions of the load area. The. effectiveness of the proposed approach has been tested on the 39-busbar New England test system.
1996
Towards a neural network based voltage stability assessment / Cory, B. J.; Knight, U. G.; Gabellone, L.; Trovato, M.. - In: ENGINEERING INTELLIGENT SYSTEMS FOR ELECTRICAL ENGINEERING AND COMMUNICATIONS. - ISSN 1472-8915. - STAMPA. - 4:1(1996), pp. 25-31.
File in questo prodotto:
Non ci sono file associati a questo prodotto.

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11589/11646
Citazioni
  • Scopus 0
  • ???jsp.display-item.citation.isi??? 0
social impact