DocumentCode
173494
Title
Selection of measurements in topology estimation with mutual information
Author
Krstulovic, Jakov ; Miranda, V.
Author_Institution
FESB, Univ. of Split, Split, Croatia
fYear
2014
fDate
13-16 May 2014
Firstpage
589
Lastpage
596
Abstract
This paper discusses mechanisms for establishing an efficient decentralized methodology for the reconstruction of topology in power systems. The maximum mutual information criterion is proposed as a selection criterion for the inputs of a distributed topology estimator, based on mosaic of local auto-associative neural networks. The proposed concepts offer some strong theoretical support for an information theoretic perspective on power system state estimation. The results are confirmed by extensive tests conducted on the IEEE RTS 24-bus system.
Keywords
IEEE standards; feature selection; information theory; neural nets; power system simulation; state estimation; IEEE RTS 24-bus system; auto-associative neural networks; distributed topology estimator; mutual information; power system state estimation; power systems; topology estimation; topology reconstruction; Mutual information; Network topology; Observability; Power systems; State estimation; Topology; Mutual information; autoencoders; feature selection; power system topology estimation;
fLanguage
English
Publisher
ieee
Conference_Titel
Energy Conference (ENERGYCON), 2014 IEEE International
Conference_Location
Cavtat
Type
conf
DOI
10.1109/ENERGYCON.2014.6850486
Filename
6850486
Link To Document