Publication type: Article in scientific journal
Type of review: Peer review (publication)
Title: Fast-training feedforward neural network for multi-scale power quality monitoring in power systems with distributed generation sources
Authors: Cortes-Robles, Oswaldo
Barocio, Emilio
Obusevs, Artjoms
Korba, Petr
Segundo Sevilla, Felix Rafael
et. al: No
DOI: 10.1016/j.measurement.2020.108690
Published in: Measurement
Volume(Issue): 170
Issue: 108690
Issue Date: 2021
Publisher / Ed. Institution: Elsevier
ISSN: 0263-2241
1873-412X
Language: English
Subjects: Power quality; Disturbance classification; Variational mode decomposition; Deep learning; Distributed generation sources
Subject (DDC): 006: Special computer methods
621.3: Electrical, communications, control engineering
Abstract: In this paper, a deep learning approach for power quality monitoring in systems with distributed generation sources is presented. The proposed method focuses in the multi-scale analysis of multi-component signals for power quality disturbances classification. The proposed methodology combines a signal processing stage using variational mode decomposition (VMD) to obtain the times scales of multi-component signals, and a deep learning stage using a simple feedforward neural network (FFNN) to classify the disturbances. The simple proposed architecture allows minimum training time of the classification model. In addition, the proposed method is able to classify different disturbance combinations based on a reduced training-set. The proposed VMD-FFNN method is tested using synthetic and simulated signals, and it is compared with other well-known methods based on convolutional and recurrent deep neuronal networks. Finally, the proposed method is assessed using lab measurements in order to shown its performance in a real-world environment.
URI: https://digitalcollection.zhaw.ch/handle/11475/23777
Fulltext version: Published version
License (according to publishing contract): Licence according to publishing contract
Departement: School of Engineering
Organisational Unit: Institute of Energy Systems and Fluid Engineering (IEFE)
Appears in collections:Publikationen School of Engineering

Files in This Item:
There are no files associated with this item.
Show full item record
Cortes-Robles, O., Barocio, E., Obusevs, A., Korba, P., & Segundo Sevilla, F. R. (2021). Fast-training feedforward neural network for multi-scale power quality monitoring in power systems with distributed generation sources. Measurement, 170(108690). https://doi.org/10.1016/j.measurement.2020.108690
Cortes-Robles, O. et al. (2021) ‘Fast-training feedforward neural network for multi-scale power quality monitoring in power systems with distributed generation sources’, Measurement, 170(108690). Available at: https://doi.org/10.1016/j.measurement.2020.108690.
O. Cortes-Robles, E. Barocio, A. Obusevs, P. Korba, and F. R. Segundo Sevilla, “Fast-training feedforward neural network for multi-scale power quality monitoring in power systems with distributed generation sources,” Measurement, vol. 170, no. 108690, 2021, doi: 10.1016/j.measurement.2020.108690.
CORTES-ROBLES, Oswaldo, Emilio BAROCIO, Artjoms OBUSEVS, Petr KORBA und Felix Rafael SEGUNDO SEVILLA, 2021. Fast-training feedforward neural network for multi-scale power quality monitoring in power systems with distributed generation sources. Measurement. 2021. Bd. 170, Nr. 108690. DOI 10.1016/j.measurement.2020.108690
Cortes-Robles, Oswaldo, Emilio Barocio, Artjoms Obusevs, Petr Korba, and Felix Rafael Segundo Sevilla. 2021. “Fast-Training Feedforward Neural Network for Multi-Scale Power Quality Monitoring in Power Systems with Distributed Generation Sources.” Measurement 170 (108690). https://doi.org/10.1016/j.measurement.2020.108690.
Cortes-Robles, Oswaldo, et al. “Fast-Training Feedforward Neural Network for Multi-Scale Power Quality Monitoring in Power Systems with Distributed Generation Sources.” Measurement, vol. 170, no. 108690, 2021, https://doi.org/10.1016/j.measurement.2020.108690.


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.