Reconstructing missing data in state estimation with autoencoders

This paper presents the proof of concept for a new solution to the problem of recomposing missing information at the SCADA of energy/distribution management systems (EMS/DMS), through the use of offline trained autoencoders. These are neural networks with a special architecture, which allows them to...

Full description

Bibliographic Details
Main Author: Vladimiro Miranda (author)
Other Authors: Jakov Krstulovic (author), Hrvoje Keko (author), Cristiano Moreira (author), Jorge Pereira (author)
Format: article
Language:eng
Published: 2012
Subjects:
Engenharia electrotécnica, Engenharia electrotécnica, electrónica e informática
Electrical engineering, Electrical engineering, Electronic engineering, Information engineering
Online Access:https://hdl.handle.net/10216/96487
Country:Portugal
Oai:oai:repositorio-aberto.up.pt:10216/96487

Internet

https://hdl.handle.net/10216/96487

Similar Items