Machine learning based impedance estimation in power system

Kamyab Givaki, Saleh Seyedzadeh, Kamyar GIvaki

Research output: Contribution to conferencePaper

Abstract

A passive machine learning based technique to estimate the impedance of the power grid at the point of common coupling of a converter interfaced distributed generation source is proposed. The proposed method is based on supervised learning and provides a fast and accurate estimation of the grid impedance without adversely impacting the power quality of the system. This method does not need an injection of additional signals to the grid and provides an accurate estimation of the grid impedance. Multi-objective NSGA-II algorithm is used for optimisation and tuning the random forest model for accurate estimation of both R and X The resistive and inductive reactance of grid is estimated using Random Forest model due to its capability in the prediction of multiple output values simultaneously.

Conference

Conference8th International Conference on Renewable Power Generation
Abbreviated titleRPG
CountryChina
CityShanghai
Period24/10/1925/10/19
Internet address

Fingerprint

Learning systems
Supervised learning
Distributed power generation
Power quality
Tuning

Keywords

  • impedance estimation
  • machine learning
  • power system stability
  • random forest model
  • supervised learning

Cite this

Givaki, K., Seyedzadeh, S., & GIvaki, K. (Accepted/In press). Machine learning based impedance estimation in power system. Paper presented at 8th International Conference on Renewable Power Generation, Shanghai, China.
Givaki, Kamyab ; Seyedzadeh, Saleh ; GIvaki, Kamyar. / Machine learning based impedance estimation in power system. Paper presented at 8th International Conference on Renewable Power Generation, Shanghai, China.6 p.
@conference{a6020ba16d434a87885ff9f217535500,
title = "Machine learning based impedance estimation in power system",
abstract = "A passive machine learning based technique to estimate the impedance of the power grid at the point of common coupling of a converter interfaced distributed generation source is proposed. The proposed method is based on supervised learning and provides a fast and accurate estimation of the grid impedance without adversely impacting the power quality of the system. This method does not need an injection of additional signals to the grid and provides an accurate estimation of the grid impedance. Multi-objective NSGA-II algorithm is used for optimisation and tuning the random forest model for accurate estimation of both R and X The resistive and inductive reactance of grid is estimated using Random Forest model due to its capability in the prediction of multiple output values simultaneously.",
keywords = "impedance estimation, machine learning, power system stability, random forest model, supervised learning",
author = "Kamyab Givaki and Saleh Seyedzadeh and Kamyar GIvaki",
year = "2019",
month = "4",
day = "29",
language = "English",
note = "8th International Conference on Renewable Power Generation, RPG ; Conference date: 24-10-2019 Through 25-10-2019",
url = "http://rpg2019.events.theiet.org.cn/",

}

Givaki, K, Seyedzadeh, S & GIvaki, K 2019, 'Machine learning based impedance estimation in power system' Paper presented at 8th International Conference on Renewable Power Generation, Shanghai, China, 24/10/19 - 25/10/19, .

Machine learning based impedance estimation in power system. / Givaki, Kamyab; Seyedzadeh, Saleh; GIvaki, Kamyar.

2019. Paper presented at 8th International Conference on Renewable Power Generation, Shanghai, China.

Research output: Contribution to conferencePaper

TY - CONF

T1 - Machine learning based impedance estimation in power system

AU - Givaki, Kamyab

AU - Seyedzadeh, Saleh

AU - GIvaki, Kamyar

PY - 2019/4/29

Y1 - 2019/4/29

N2 - A passive machine learning based technique to estimate the impedance of the power grid at the point of common coupling of a converter interfaced distributed generation source is proposed. The proposed method is based on supervised learning and provides a fast and accurate estimation of the grid impedance without adversely impacting the power quality of the system. This method does not need an injection of additional signals to the grid and provides an accurate estimation of the grid impedance. Multi-objective NSGA-II algorithm is used for optimisation and tuning the random forest model for accurate estimation of both R and X The resistive and inductive reactance of grid is estimated using Random Forest model due to its capability in the prediction of multiple output values simultaneously.

AB - A passive machine learning based technique to estimate the impedance of the power grid at the point of common coupling of a converter interfaced distributed generation source is proposed. The proposed method is based on supervised learning and provides a fast and accurate estimation of the grid impedance without adversely impacting the power quality of the system. This method does not need an injection of additional signals to the grid and provides an accurate estimation of the grid impedance. Multi-objective NSGA-II algorithm is used for optimisation and tuning the random forest model for accurate estimation of both R and X The resistive and inductive reactance of grid is estimated using Random Forest model due to its capability in the prediction of multiple output values simultaneously.

KW - impedance estimation

KW - machine learning

KW - power system stability

KW - random forest model

KW - supervised learning

M3 - Paper

ER -

Givaki K, Seyedzadeh S, GIvaki K. Machine learning based impedance estimation in power system. 2019. Paper presented at 8th International Conference on Renewable Power Generation, Shanghai, China.