On-line supervised learning for dynamic security classification using probabilistic neural networks

Gavoyiannis, AE; Voumvoulakis, EM; Hatziargyriou, ND

dc.contributor.author	Gavoyiannis, AE	en
dc.contributor.author	Voumvoulakis, EM	en
dc.contributor.author	Hatziargyriou, ND	en
dc.date.accessioned	2014-03-01T02:43:27Z
dc.date.available	2014-03-01T02:43:27Z
dc.date.issued	2005	en
dc.identifier.uri	https://dspace.lib.ntua.gr/xmlui/handle/123456789/31418
dc.subject	Dynamic Security	en
dc.subject	Gaussian Mixtures	en
dc.subject	Isolated Systems	en
dc.subject	Maximum Likelihood (ML)	en
dc.subject	On-line learning	en
dc.subject	Probabilistic Neural Network (PNN)	en
dc.subject	Probability Density Function (PDF)	en
dc.subject.other	Dynamic security	en
dc.subject.other	Gaussian mixtures	en
dc.subject.other	Isolated systems	en
dc.subject.other	On-line learning	en
dc.subject.other	Probabilistic neural network (PNN)	en
dc.subject.other	Classification (of information)	en
dc.subject.other	Decision making	en
dc.subject.other	Electric power systems	en
dc.subject.other	Maximum likelihood estimation	en
dc.subject.other	Online systems	en
dc.subject.other	Pattern recognition	en
dc.subject.other	Probability density function	en
dc.subject.other	Security systems	en
dc.subject.other	Neural networks	en
dc.title	On-line supervised learning for dynamic security classification using probabilistic neural networks	en
heal.type	conferenceItem	en
heal.identifier.primary	10.1109/PES.2005.1489656	en
heal.identifier.secondary	http://dx.doi.org/10.1109/PES.2005.1489656	en
heal.publicationDate	2005	en
heal.abstract	This paper addresses the problem of dynamic security classification of electric power systems using multiclass pattern recognition. In particular, on-line supervised learning using Probabilistic Neural Networks is applied. The various patterns are recognized by calculating probabilities of belonging to each class. These probabilities are used in a subsequent decision-making stage to achieve classification. The learning of each class can be performed in parallel. Results regarding performance of the proposed pattern recognition tested on the dynamic security of an actual island power system are presented and discussed. © 2005 IEEE.	en
heal.journalName	2005 IEEE Power Engineering Society General Meeting	en
dc.identifier.doi	10.1109/PES.2005.1489656	en
dc.identifier.volume	3	en
dc.identifier.spage	2669	en
dc.identifier.epage	2675	en