Through the looking glass: Seeing events in power systems dynamics

• Tipo: Artigo em Revista Científica Internacional
• Data: 2019

Autores

Vladimiro Miranda (Autor) FEUP; Pedro A. Cardoso (Autor) Outra; Ricardo J. Bessa (Autor) Outra; Ildemar Decker (Autor) Outra

Revista

Título: International Journal of Electrical Power and Energy Systems

Vol. 106

Páginas: 411-419

ISSN: 0142-0615

Editora: Elsevier

Indexação

ISI Web of Knowledge - 3 Citações

ISI Web of Science

Scopus - 5 Citações

Outras Informações

ID Authenticus: P-00P-ST5

DOI: 10.1016/j.ijepes.2018.10.024

Abstract (EN): This paper presents a new method to identify classes of events, by processing phasor measurement units (PMU) frequency data through deep neural networks. Deep tapered Multi-layer Perceptrons of the half-autoencoder type, Deep Belief Networks and Convolutional Neural Networks (CNN) are compared, using real data from Brazil. A sound success is obtained by a transformation of time-domain signals, from dynamic events recorded, into 2D images; these images wee processed with a CNN, taking advantage of the strong dependency existing among neighboring pixels in images. The training, computing and processing was achieved with a GPU (Graphics Processing Unit), allowing speeding-up of the process up to 30 times and rendering the process suitable to increase the online situational awareness of network operators. © 2018

Idioma: Inglês

Tipo (Avaliação Docente): Científica

Nº de páginas: 9