Generator rotor angle oscillations can be caused by sudden changes in its mechanical power input or its electrical power output. When dampening or synchronizing torque is inadequate, rotor angle instability occurs, resulting in an increase in rotor angle, loss of synchronism, or oscillatory swings of the rotor angle with increasing amplitude. To this end, in this work, we offer a novel two-stage approach for predicting rotor angle stability following a large disturbance. The process begins with the creation of a database of dynamic simulation scenarios. This collection contains a wide set of stable and unstable rotor angle trajectories derived from different fault simulations. Then, the fuzzy c-means (FCM) clustering algorithm is utilized to put the sampled data of rotor angles with the highest degree of similarity in the same cluster. Angle sets generated by FCM are used to train the adaptive neuro-fuzzy inference system (ANFIS). Finally, the trained ANFIS is used to predict the future rotor angle stability situation of generators. In addition, a stability index is suggested in this article, which will assist ANFIS in more accurately predicting the stability condition. The efficiency of the proposed method is tested on the IEEE 39-bus system. The obtained results from simulations confirm that the proposed strategy can correctly predict the rotor angle instability or stability situation of generators in a few cycles after fault clearance.

A two-stage strategy for generator rotor angle stability prediction using the adaptive neuro-fuzzy inference system

Siano P.
2023-01-01

Abstract

Generator rotor angle oscillations can be caused by sudden changes in its mechanical power input or its electrical power output. When dampening or synchronizing torque is inadequate, rotor angle instability occurs, resulting in an increase in rotor angle, loss of synchronism, or oscillatory swings of the rotor angle with increasing amplitude. To this end, in this work, we offer a novel two-stage approach for predicting rotor angle stability following a large disturbance. The process begins with the creation of a database of dynamic simulation scenarios. This collection contains a wide set of stable and unstable rotor angle trajectories derived from different fault simulations. Then, the fuzzy c-means (FCM) clustering algorithm is utilized to put the sampled data of rotor angles with the highest degree of similarity in the same cluster. Angle sets generated by FCM are used to train the adaptive neuro-fuzzy inference system (ANFIS). Finally, the trained ANFIS is used to predict the future rotor angle stability situation of generators. In addition, a stability index is suggested in this article, which will assist ANFIS in more accurately predicting the stability condition. The efficiency of the proposed method is tested on the IEEE 39-bus system. The obtained results from simulations confirm that the proposed strategy can correctly predict the rotor angle instability or stability situation of generators in a few cycles after fault clearance.
2023
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/11386/4853059
 Attenzione

Attenzione! I dati visualizzati non sono stati sottoposti a validazione da parte dell'ateneo

Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 2
  • ???jsp.display-item.citation.isi??? 2
social impact