Transient stability assessment using artificial neural networks

A. R. Edwards, K. W. Chan, R. W. Dunn, A. R. Daniels

Research output: Unpublished conference presentation (presented paper, abstract, poster)Conference presentation (not published in journal/proceeding/book)Academic researchpeer-review


This paper discusses a method for fast transient stability assessment of large interconnected power systems. Composite indices, such as the minimum post-contingency busbar voltage magnitude and sum of the changes in rotor angles, provide an effective method for reducing the dimensionality of feature vectors for transient stability classification. Typically, less than 20 composite indices are required to construct a feature vector for a contingency, which can then be classified using an artificial neural network into a transiently stable or unstable contingency. Simulation results are presented for an IEEE test network as well as a reduced model of the UK National Grid System, and the application of this technique to contingency screening in an Energy Management System is discussed.

Original languageEnglish
Number of pages4
Publication statusPublished - Sept 1994
EventProceedings of the 29th Universities Power Engineering Conference. Part 2 (of 2) - Galway, Irel
Duration: 14 Sept 199416 Sept 1994


ConferenceProceedings of the 29th Universities Power Engineering Conference. Part 2 (of 2)
CityGalway, Irel

ASJC Scopus subject areas

  • Engineering(all)


Dive into the research topics of 'Transient stability assessment using artificial neural networks'. Together they form a unique fingerprint.

Cite this