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
• ISSN: 0378-7796; 1873-2046
• DOI: 10.1016/j.epsr.2017.12.026

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 to produce the best results.•The scheme repairs vectors with up to 4 gross errors simultaneously. This paper presents a new concept for an approach to deal with measurements contaminated with gross errors, prior to power system state estimation. Instead of a simple filtering operation, the new procedure develops a screen-and-repair process, going through the phases of detection, identification and correction of multiple gross errors. The method is based on the definition of the coverage of the measurement set by a tiling scheme of 3-overlapping autoencoders, trained with denoising techniques and correntropy, that produce an ensemble-like set of three proposals for each measurement. These proposals are then subject to a process of fusion to produce a vector of proposed/corrected measurements, and two fusion methods are compared, with advantage to the Parzen Windows method. The original measurement vector can then be recognized as clean or diagnosed with possible gross errors, together with corrections that remove these errors. The repaired vectors can then serve as input to classical state estimation procedures, as only a small noise remains. A test case illustrates the effectiveness of the technique, which could deal with four simultaneous gross errors and achieve a result close to full recognition and correction of the errors.