An artificial neural-net based technique for power system dynamic stability with the Kohonen model

Hiroyuki Mori, Yoshihito Tamaru, Senji Tsuzuki

Research output: Chapter in Book/Report/Conference proceedingConference contribution

8 Citations (Scopus)

Abstract

An artificial neural network-based method for evaluating online power system dynamic stability is presented. Using the matrix transformation of the S-matrix method, the absolute value of the most critical eigenvalue in z-plane may be regarded as a power system dynamic stability index. The artificial neural net of Kohonen is used to estimate the index so that computational efforts are reduced and numerical instability problems are avoided. The Kohonen model is based on the self-organization feature mapping (SOFM) technique that transforms input patterns into neurons on the two-dimensional grid. The algorithm used does not require the teacher's signals and is not too complicated, and the resulting mapping makes it visually easy to understand the input pattern. Power system conditions are assigned to the output neurons on the two-dimensional grid with the SOFM technique. Two methods are presented to calculate the estimate index so that an output neuron calls the index corresponding to an input pattern. The linear and nonlinear decreasing function employed at the learning process are compared. The effectiveness of the proposed method is demonstrated.

Original languageEnglish
Title of host publication91 IEEE Power Ind Comput Appl Conf Presented 17 PICA Conf
PublisherPubl by IEEE
Pages293-301
Number of pages9
ISBN (Print)0879426209
Publication statusPublished - 1 Jan 1992
Event1991 IEEE Power Industry Computer Application Conference presented at the 17th PICA Conference - Baltimore, MD, USA
Duration: 7 May 199110 May 1991

Publication series

Name91 IEEE Power Ind Comput Appl Conf Presented 17 PICA Conf

Conference

Conference1991 IEEE Power Industry Computer Application Conference presented at the 17th PICA Conference
CityBaltimore, MD, USA
Period7/05/9110/05/91

    Fingerprint

Cite this

Mori, H., Tamaru, Y., & Tsuzuki, S. (1992). An artificial neural-net based technique for power system dynamic stability with the Kohonen model. In 91 IEEE Power Ind Comput Appl Conf Presented 17 PICA Conf (pp. 293-301). (91 IEEE Power Ind Comput Appl Conf Presented 17 PICA Conf). Publ by IEEE.