A machine learning approach for active/reactive power control of grid-connected doubly-fed induction generators

Jafar Tavoosi; Ardashir Mohammadzadeh; Bahareh Pahlevanzadeh; Morad Bagherzadeh Kasmani; Shahab S. Band; Rabia Safdar; Amir H. Mosavi

doi:10.1016/j.asej.2021.08.007

A machine learning approach for active/reactive power control of grid-connected doubly-fed induction generators

Jafar Tavoosi, Ardashir Mohammadzadeh, Bahareh Pahlevanzadeh, Morad Bagherzadeh Kasmani, Shahab S. Band, Rabia Safdar, Amir H. Mosavi

Research output: Contribution to journal › Article › peer-review

Abstract

This paper suggests a new fuzzy method for active power (AP) and reactive power (RP) control of a power grid that includes wind turbines and Doubly Fed Induction Generators (DFIGs). A Recurrent Type-II Fuzzy Neural Networks (RT2FNN) controller based on Radial Basis Function Networks (RBFN) is applied to the rotor side converter for the power control and voltage regulation of the wind turbine equipped with the DFIG. In order to train a model, the voltage profile at each bus, and the reactive power of the power grid are given to the RT2FNN as the input and output, respectively. A wind turbine and its control units are studied in detail. Simulation results, obtained in MATLAB software, show the well performance, robustness, good accuracy and power quality improvement of the suggested controller in the wind-driven DFIGs.

Original language	English
Article number	101564
Journal	Ain Shams Engineering Journal
Volume	13
Issue number	2
DOIs	https://doi.org/10.1016/j.asej.2021.08.007
Publication status	Published - Mar 2022
Externally published	Yes

Keywords

Active/reactive power
Artificial intelligence
Doubly-Fed Induction Generator (DFIG)
Radial Basis Function Network (RBFN)
Recurrent Type-II Fuzzy Neural Networks (RT2FNN)
Renewable energies
Wind turbine

Access to Document

10.1016/j.asej.2021.08.007

Cite this

@article{482e9872c3664dde9ce9243d25bb7922,

title = "A machine learning approach for active/reactive power control of grid-connected doubly-fed induction generators",

abstract = "This paper suggests a new fuzzy method for active power (AP) and reactive power (RP) control of a power grid that includes wind turbines and Doubly Fed Induction Generators (DFIGs). A Recurrent Type-II Fuzzy Neural Networks (RT2FNN) controller based on Radial Basis Function Networks (RBFN) is applied to the rotor side converter for the power control and voltage regulation of the wind turbine equipped with the DFIG. In order to train a model, the voltage profile at each bus, and the reactive power of the power grid are given to the RT2FNN as the input and output, respectively. A wind turbine and its control units are studied in detail. Simulation results, obtained in MATLAB software, show the well performance, robustness, good accuracy and power quality improvement of the suggested controller in the wind-driven DFIGs.",

keywords = "Active/reactive power, Artificial intelligence, Doubly-Fed Induction Generator (DFIG), Radial Basis Function Network (RBFN), Recurrent Type-II Fuzzy Neural Networks (RT2FNN), Renewable energies, Wind turbine",

author = "Jafar Tavoosi and Ardashir Mohammadzadeh and Bahareh Pahlevanzadeh and Kasmani, {Morad Bagherzadeh} and Band, {Shahab S.} and Rabia Safdar and Mosavi, {Amir H.}",

note = "Publisher Copyright: {\textcopyright} 2021 THE AUTHORS",

year = "2022",

month = mar,

doi = "10.1016/j.asej.2021.08.007",

language = "English",

volume = "13",

journal = "Ain Shams Engineering Journal",

issn = "2090-4479",

publisher = "Ain Shams University",

number = "2",

}

TY - JOUR

T1 - A machine learning approach for active/reactive power control of grid-connected doubly-fed induction generators

AU - Tavoosi, Jafar

AU - Mohammadzadeh, Ardashir

AU - Pahlevanzadeh, Bahareh

AU - Kasmani, Morad Bagherzadeh

AU - Band, Shahab S.

AU - Safdar, Rabia

AU - Mosavi, Amir H.

PY - 2022/3

Y1 - 2022/3

N2 - This paper suggests a new fuzzy method for active power (AP) and reactive power (RP) control of a power grid that includes wind turbines and Doubly Fed Induction Generators (DFIGs). A Recurrent Type-II Fuzzy Neural Networks (RT2FNN) controller based on Radial Basis Function Networks (RBFN) is applied to the rotor side converter for the power control and voltage regulation of the wind turbine equipped with the DFIG. In order to train a model, the voltage profile at each bus, and the reactive power of the power grid are given to the RT2FNN as the input and output, respectively. A wind turbine and its control units are studied in detail. Simulation results, obtained in MATLAB software, show the well performance, robustness, good accuracy and power quality improvement of the suggested controller in the wind-driven DFIGs.

AB - This paper suggests a new fuzzy method for active power (AP) and reactive power (RP) control of a power grid that includes wind turbines and Doubly Fed Induction Generators (DFIGs). A Recurrent Type-II Fuzzy Neural Networks (RT2FNN) controller based on Radial Basis Function Networks (RBFN) is applied to the rotor side converter for the power control and voltage regulation of the wind turbine equipped with the DFIG. In order to train a model, the voltage profile at each bus, and the reactive power of the power grid are given to the RT2FNN as the input and output, respectively. A wind turbine and its control units are studied in detail. Simulation results, obtained in MATLAB software, show the well performance, robustness, good accuracy and power quality improvement of the suggested controller in the wind-driven DFIGs.

KW - Active/reactive power

KW - Artificial intelligence

KW - Doubly-Fed Induction Generator (DFIG)

KW - Radial Basis Function Network (RBFN)

KW - Recurrent Type-II Fuzzy Neural Networks (RT2FNN)

KW - Renewable energies

KW - Wind turbine

UR - http://www.scopus.com/inward/record.url?scp=85114095933&partnerID=8YFLogxK

U2 - 10.1016/j.asej.2021.08.007

DO - 10.1016/j.asej.2021.08.007

M3 - Article

AN - SCOPUS:85114095933

SN - 2090-4479

VL - 13

JO - Ain Shams Engineering Journal

JF - Ain Shams Engineering Journal

IS - 2

M1 - 101564

ER -

A machine learning approach for active/reactive power control of grid-connected doubly-fed induction generators

Abstract

Keywords

Access to Document

Fingerprint

Cite this