State estimation pre-filtering with overlapping tiling of autoencoders

• Published in: Electric power systems research Vol. 157; pp. 261 - 271
• Main Authors: Saran, Marco A.M., Miranda, Vladimiro
• Format: Journal Article
• Language: English
• Published: Amsterdam Elsevier B.V 01.04.2018; Elsevier Science Ltd
• Subjects: Autoencoder; Bad data; Correntropy; Data fusion; Electricity distribution; Errors; Filtration; Fusion; Gross error; Neural network; Neural networks; Noise reduction; Proposals; State estimation; Tiling; Correntropy; Autoencoder; Bad data; Data fusion; Neural network; Gross error; State estimation

Core findings. •A feasible implementation of a screen-and-repair pre-filtering procedure proposed.•An overlapping tiling of autoencoders designed under information theory principles.•An ensemble of corrected measurements generated by local autoencoders.•A Parzen Windows data fusion process is shown...