Adaptive protection combined with machine learning for microgrids

Research output: Contribution to journalJournal articleResearchpeer-review

Abstract

This paper presents a rule-based adaptive protection scheme using machine-learning methodology for microgrids in extensive distribution automation (DA). The uncertain elements in a microgrid are first analysed quantitatively by Pearson correlation coefficients from data mining. Then, a so-called hybrid artificial neural network and support vector machine (ANN-SVM) model is proposed for state recognition in microgrids, which utilises the growing massive data streams in smart grids. Based on the state recognition in the algorithm, adaptive reconfigurations can be implemented with enhanced decision-making to modify the protective settings and the network topology to ensure the reliability of the intelligent operation. The effectiveness of the proposed methods is demonstrated on a microgrid model in Aalborg, Denmark and an IEEE 9 bus model, respectively.
Original languageEnglish
JournalIET Generation, Transmission and Distribution
Volume13
Issue number6
Pages (from-to)770-779
Number of pages10
ISSN1751-8687
DOIs
Publication statusPublished - Mar 2019

Fingerprint

Learning systems
Adaptive algorithms
Support vector machines
Data mining
Automation
Decision making
Topology
Neural networks

Keywords

  • Power engineering computing
  • Support vector machines
  • Neural nets
  • Smart power grids
  • Learning (artificial intelligence)
  • Data mining
  • Distributed power generation

Cite this

@article{1cc818871fe24d87b3b9b4d21c0e0009,
title = "Adaptive protection combined with machine learning for microgrids",
abstract = "This paper presents a rule-based adaptive protection scheme using machine-learning methodology for microgrids in extensive distribution automation (DA). The uncertain elements in a microgrid are first analysed quantitatively by Pearson correlation coefficients from data mining. Then, a so-called hybrid artificial neural network and support vector machine (ANN-SVM) model is proposed for state recognition in microgrids, which utilises the growing massive data streams in smart grids. Based on the state recognition in the algorithm, adaptive reconfigurations can be implemented with enhanced decision-making to modify the protective settings and the network topology to ensure the reliability of the intelligent operation. The effectiveness of the proposed methods is demonstrated on a microgrid model in Aalborg, Denmark and an IEEE 9 bus model, respectively.",
keywords = "Power engineering computing, Support vector machines, Neural nets, Smart power grids, Learning (artificial intelligence), Data mining, Distributed power generation",
author = "Hengwei Lin and Kai Sun and Tan, {Zheng Hua} and Chengxi Liu and Guerrero, {Josep M.} and Vasquez, {Juan C.}",
year = "2019",
month = "3",
doi = "10.1049/iet-gtd.2018.6230",
language = "English",
volume = "13",
pages = "770--779",
journal = "IET Generation, Transmission & Distribution",
issn = "1751-8687",
publisher = "Institution of Engineering and Technology",
number = "6",

}

Adaptive protection combined with machine learning for microgrids. / Lin, Hengwei; Sun, Kai; Tan, Zheng Hua; Liu, Chengxi; Guerrero, Josep M.; Vasquez, Juan C.

In: IET Generation, Transmission and Distribution, Vol. 13, No. 6, 03.2019, p. 770-779.

Research output: Contribution to journalJournal articleResearchpeer-review

TY - JOUR

T1 - Adaptive protection combined with machine learning for microgrids

AU - Lin, Hengwei

AU - Sun, Kai

AU - Tan, Zheng Hua

AU - Liu, Chengxi

AU - Guerrero, Josep M.

AU - Vasquez, Juan C.

PY - 2019/3

Y1 - 2019/3

N2 - This paper presents a rule-based adaptive protection scheme using machine-learning methodology for microgrids in extensive distribution automation (DA). The uncertain elements in a microgrid are first analysed quantitatively by Pearson correlation coefficients from data mining. Then, a so-called hybrid artificial neural network and support vector machine (ANN-SVM) model is proposed for state recognition in microgrids, which utilises the growing massive data streams in smart grids. Based on the state recognition in the algorithm, adaptive reconfigurations can be implemented with enhanced decision-making to modify the protective settings and the network topology to ensure the reliability of the intelligent operation. The effectiveness of the proposed methods is demonstrated on a microgrid model in Aalborg, Denmark and an IEEE 9 bus model, respectively.

AB - This paper presents a rule-based adaptive protection scheme using machine-learning methodology for microgrids in extensive distribution automation (DA). The uncertain elements in a microgrid are first analysed quantitatively by Pearson correlation coefficients from data mining. Then, a so-called hybrid artificial neural network and support vector machine (ANN-SVM) model is proposed for state recognition in microgrids, which utilises the growing massive data streams in smart grids. Based on the state recognition in the algorithm, adaptive reconfigurations can be implemented with enhanced decision-making to modify the protective settings and the network topology to ensure the reliability of the intelligent operation. The effectiveness of the proposed methods is demonstrated on a microgrid model in Aalborg, Denmark and an IEEE 9 bus model, respectively.

KW - Power engineering computing

KW - Support vector machines

KW - Neural nets

KW - Smart power grids

KW - Learning (artificial intelligence)

KW - Data mining

KW - Distributed power generation

UR - http://www.scopus.com/inward/record.url?scp=85065123441&partnerID=8YFLogxK

U2 - 10.1049/iet-gtd.2018.6230

DO - 10.1049/iet-gtd.2018.6230

M3 - Journal article

VL - 13

SP - 770

EP - 779

JO - IET Generation, Transmission & Distribution

JF - IET Generation, Transmission & Distribution

SN - 1751-8687

IS - 6

ER -