Pregled bibliografske jedinice broj: 579431
Reconstructing Missing Data in State Estimation With Autoencoders
Reconstructing Missing Data in State Estimation With Autoencoders // IEEE transactions on power systems, 27 (2012), 2; 604-611 doi:10.1109/TPWRS.2011.2174810 (međunarodna recenzija, članak, znanstveni)
CROSBI ID: 579431 Za ispravke kontaktirajte CROSBI podršku putem web obrasca
Naslov
Reconstructing Missing Data in State Estimation With Autoencoders
Autori
Miranda, Vladimiro ; Krstulović, Jakov ; Keko, Hrvoje ; Moreira Cristiano ; Pereira, Jorge
Izvornik
IEEE transactions on power systems (0885-8950) 27
(2012), 2;
604-611
Vrsta, podvrsta i kategorija rada
Radovi u časopisima, članak, znanstveni
Ključne riječi
autoencoders; distribution management systems; energy management systems; neural networks; state estimation
Sažetak
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.
Izvorni jezik
Engleski
Znanstvena područja
Elektrotehnika
Citiraj ovu publikaciju:
Časopis indeksira:
- Current Contents Connect (CCC)
- Web of Science Core Collection (WoSCC)
- Science Citation Index Expanded (SCI-EXP)
- SCI-EXP, SSCI i/ili A&HCI
- Scopus
