Reconstructing Missing Data in State Estimation With Autoencoders (CROSBI ID 183901)
Prilog u časopisu | izvorni znanstveni rad | međunarodna recenzija
Podaci o odgovornosti
Miranda, Vladimiro ; Krstulović, Jakov ; Keko, Hrvoje ; Moreira Cristiano ; Pereira, Jorge
engleski
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 EMS/DMS (Energy/Distribution Management Systems), through the use of off-line trained autoencoders. These are neural networks with a special architecture, which allows them to store knowledge about a system in a non-linear manifold characterized by their weights. Suitable algorithms may then recompose missing inputs (measurements). The paper shows that, trained with adequate information, autoencoders perform well in recomposing missing voltage and power values, and focuses on the particularly important application of inferring the topology of the network when information about switch status is absent. Examples with the IEEE RTS 24 bus network are presented to illustrate the concept and technique.
autoencoders; distribution management systems; energy management systems; neural networks; state estimation
nije evidentirano
nije evidentirano
nije evidentirano
nije evidentirano
nije evidentirano
nije evidentirano
Podaci o izdanju
27 (2)
2012.
604-611
objavljeno
0885-8950
10.1109/TPWRS.2011.2174810