Fast learning algorithm for synchronous generator instability prediction

George G. Karady, Ahmed A. Daoud, Mansour A. Mohammed, Ibrahim A. Amin

Research output: Contribution to journalArticlepeer-review

Abstract

This paper proposes a new method of power system instability prediction. The proposed method does not require any prior knowledge of the power system parameters. After fault clearing in the power system the generators' relative rotor angles are measured for about 0.3-0.5 second and the variation of each generator rotor angle is predicted for the next 0.5-2 second period using the developed algorithm and the measured data. If a generator rotor angle is larger than an experimentally determined threshold, the system is considered unstable and remedial actions are initiated. The WECC test system is used to prove the validity of the proposed method for generator relative rotor angle prediction. The study indicated that the prediction error is less than 10%.

Original languageEnglish (US)
Pages (from-to)67-72
Number of pages6
JournalEngineering Intelligent Systems
Volume12
Issue number2
StatePublished - Jun 2004

Keywords

  • Fast learning algorithm
  • Generator instability prediction
  • Power systems
  • WECC test system

ASJC Scopus subject areas

  • Control and Systems Engineering
  • Computer Science Applications
  • Electrical and Electronic Engineering

Fingerprint

Dive into the research topics of 'Fast learning algorithm for synchronous generator instability prediction'. Together they form a unique fingerprint.

Cite this