A two-level neural network approach for flicker source location

被引:7
作者
Samet, Haidar [1 ,2 ]
Khosravi, Mahdi [1 ]
Ghanbari, Teymoor [3 ]
Tajdinian, Mohsen [1 ]
机构
[1] Shiraz Univ, Sch Elect & Comp Engn, Shiraz, Iran
[2] Eindhoven Univ Technol, Dept Elect Engn, Eindhoven, Netherlands
[3] Shiraz Univ, Sch Adv Technol, Shiraz, Iran
关键词
Autoregressive Moving Average (ARMA); Flicker source identify; Power quality; Hilbert transform; ANN; MITIGATION;
D O I
10.1016/j.compeleceng.2021.107157
中图分类号
TP3 [计算技术、计算机技术];
学科分类号
0812 ;
摘要
Identification of flicker sources is necessary to find who is responsible for the measured flicker and improve power quality. This paper puts forward a new method for identifying flicker sources with minimum measurement units. Contrary to the previous works where flicker sources are considered a single-frequency signal, the autoregressive moving average (ARMA) is used to model active and reactive power variations. First, the envelope of the network voltage at the considered busbars is derived by the Hilbert transform. Then, appropriate flicker indices are extracted from the power spectral density (PSD) of the voltage envelope. A novel two-level structure of a set of ANNs is proposed, which needs a low number of voltage measurement units to locate the flicker sources. Using the captured data from different simulations of various scenarios, the Artificial Neural Networks (ANNs) are trained to categorize flicker sources.
引用
收藏
页数:17
相关论文
共 50 条
[41]   Optimal indirect model predictive control for single-phase two-level shunt active power filters [J].
Roberto Morales-Caporal .
Journal of Power Electronics, 2022, 22 :84-93
[42]   Active DC-Link Capacitor Harmonic Current Reduction in Two-Level Back-to-Back Converter [J].
Shen, Lei ;
Bozhko, Serhiy ;
Asher, Greg ;
Patel, Chintanbhai ;
Wheeler, Patrick .
IEEE TRANSACTIONS ON POWER ELECTRONICS, 2016, 31 (10) :6947-6954
[43]   Estimation of groundwater level using a hybrid genetic algorithm-neural network [J].
Hosseini, Z. ;
Nakhaei, M. .
POLLUTION, 2015, 1 (01) :9-21
[44]   A Multi-level Artificial Neural Network for Gasoline Demand Forecasting of Iran [J].
Kazemi, A. ;
Shakouri G, H. ;
Mehregan, M. R. ;
Taghizadeh, M. R. ;
Menhaj, M. B. ;
Foroughi.A, A. .
SECOND INTERNATIONAL CONFERENCE ON COMPUTER AND ELECTRICAL ENGINEERING, VOL 1, PROCEEDINGS, 2009, :61-+
[45]   Optimal indirect model predictive control for single-phase two-level shunt active power filters [J].
Morales-Caporal, Roberto .
JOURNAL OF POWER ELECTRONICS, 2022, 22 (01) :84-93
[46]   A precise electrical disturbance generator for neural network training with real level output [J].
Garcia, Antonio ;
Leon, Carlos ;
Monedero, Inigo ;
Ropero, Jorge .
PROGRESS IN PATTERN RECOGNITION, IMAGE ANALYSIS AND APPLICATIONS, PROCEEDINGS, 2007, 4756 :534-545
[47]   A Fault-Tolerant Location Approach for Transient Voltage Disturbance Source Based on Information Fusion [J].
Weng, Guoqing ;
Huang, Feiteng ;
Yan, Jun ;
Yang, Xiaodong ;
Zhang, Youbing ;
He, Haibo .
ENERGIES, 2016, 9 (12)
[48]   A novel cloud architecture approach to detect network intrusions using an enhanced artificial neural network [J].
Lakhani P. ;
Alankar B. ;
Ashraf S.S. ;
Parveen S. .
International Journal of Information Technology, 2024, 16 (6) :3929-3939
[49]   An artificial neural network approach for parametric study on welding defect classification [J].
Ho, Mei-Po ;
Ngai, Wing-Kit ;
Chan, Tai-Wing ;
Wai, Hon-wah .
INTERNATIONAL JOURNAL OF ADVANCED MANUFACTURING TECHNOLOGY, 2022, 120 (1-2) :527-535
[50]   Artificial Neural Network Based Approach for Spectrum Sensing in Cognitive Radio [J].
Yelalwar, R. G. ;
Ravinder, Y. .
2018 INTERNATIONAL CONFERENCE ON WIRELESS COMMUNICATIONS, SIGNAL PROCESSING AND NETWORKING (WISPNET), 2018,