Benchmark of machine learning algorithms on capturing future distribution network anomalies

Mostafa Mohammadpourfard, Yang Weng, Mohsen Tajdinian

Research output: Contribution to journalArticle

Abstract

The conventional distribution network is undergoing structural changes and becoming an active grid due to the advent of smart grid technologies encompassing distributed energy resources (DERs), aggregated demand response and electric vehicles (EVs). This establishes a need for state estimation-based tools and real-time monitoring of the distribution grid to correctly apply active controls. Although such new tools may be vulnerable to cyber-attacks, cyber-security of distribution grid has not received enough attention. As smart distribution grid intensively relies on communication infrastructures, the authors assume in this study that an attacker can compromise the communication and successfully conduct attacks against crucial functions of the distribution management system, making the distribution system prone to instability boundaries for collapses. They formulate the attack detection problem in the distribution grid as a statistical learning problem and demonstrate a comprehensive benchmark of statistical learning methods on various IEEE distribution test systems. The proposed learning algorithms are tested using various attack scenarios which include distinct features of modern distribution grid such as integration of DERs and EVs. Furthermore, the interaction between transmission and distribution systems and its effect on the attack detection problem are investigated. Simulation results show attack detection is more challenging in the distribution grid.

Original languageEnglish (US)
Pages (from-to)1441-1455
Number of pages15
JournalIET Generation, Transmission and Distribution
Volume13
Issue number8
DOIs
StatePublished - Jan 1 2019

Fingerprint

Energy resources
Electric vehicles
Electric power distribution
Learning algorithms
Learning systems
Communication
State estimation
Monitoring

ASJC Scopus subject areas

  • Control and Systems Engineering
  • Energy Engineering and Power Technology
  • Electrical and Electronic Engineering

Cite this

Benchmark of machine learning algorithms on capturing future distribution network anomalies. / Mohammadpourfard, Mostafa; Weng, Yang; Tajdinian, Mohsen.

In: IET Generation, Transmission and Distribution, Vol. 13, No. 8, 01.01.2019, p. 1441-1455.

Research output: Contribution to journalArticle

@article{34b918bf8d5f4ca5905d8e678ed73342,
title = "Benchmark of machine learning algorithms on capturing future distribution network anomalies",
abstract = "The conventional distribution network is undergoing structural changes and becoming an active grid due to the advent of smart grid technologies encompassing distributed energy resources (DERs), aggregated demand response and electric vehicles (EVs). This establishes a need for state estimation-based tools and real-time monitoring of the distribution grid to correctly apply active controls. Although such new tools may be vulnerable to cyber-attacks, cyber-security of distribution grid has not received enough attention. As smart distribution grid intensively relies on communication infrastructures, the authors assume in this study that an attacker can compromise the communication and successfully conduct attacks against crucial functions of the distribution management system, making the distribution system prone to instability boundaries for collapses. They formulate the attack detection problem in the distribution grid as a statistical learning problem and demonstrate a comprehensive benchmark of statistical learning methods on various IEEE distribution test systems. The proposed learning algorithms are tested using various attack scenarios which include distinct features of modern distribution grid such as integration of DERs and EVs. Furthermore, the interaction between transmission and distribution systems and its effect on the attack detection problem are investigated. Simulation results show attack detection is more challenging in the distribution grid.",
author = "Mostafa Mohammadpourfard and Yang Weng and Mohsen Tajdinian",
year = "2019",
month = "1",
day = "1",
doi = "10.1049/iet-gtd.2018.6801",
language = "English (US)",
volume = "13",
pages = "1441--1455",
journal = "IET Generation, Transmission and Distribution",
issn = "1751-8687",
publisher = "Institution of Engineering and Technology",
number = "8",

}

TY - JOUR

T1 - Benchmark of machine learning algorithms on capturing future distribution network anomalies

AU - Mohammadpourfard, Mostafa

AU - Weng, Yang

AU - Tajdinian, Mohsen

PY - 2019/1/1

Y1 - 2019/1/1

N2 - The conventional distribution network is undergoing structural changes and becoming an active grid due to the advent of smart grid technologies encompassing distributed energy resources (DERs), aggregated demand response and electric vehicles (EVs). This establishes a need for state estimation-based tools and real-time monitoring of the distribution grid to correctly apply active controls. Although such new tools may be vulnerable to cyber-attacks, cyber-security of distribution grid has not received enough attention. As smart distribution grid intensively relies on communication infrastructures, the authors assume in this study that an attacker can compromise the communication and successfully conduct attacks against crucial functions of the distribution management system, making the distribution system prone to instability boundaries for collapses. They formulate the attack detection problem in the distribution grid as a statistical learning problem and demonstrate a comprehensive benchmark of statistical learning methods on various IEEE distribution test systems. The proposed learning algorithms are tested using various attack scenarios which include distinct features of modern distribution grid such as integration of DERs and EVs. Furthermore, the interaction between transmission and distribution systems and its effect on the attack detection problem are investigated. Simulation results show attack detection is more challenging in the distribution grid.

AB - The conventional distribution network is undergoing structural changes and becoming an active grid due to the advent of smart grid technologies encompassing distributed energy resources (DERs), aggregated demand response and electric vehicles (EVs). This establishes a need for state estimation-based tools and real-time monitoring of the distribution grid to correctly apply active controls. Although such new tools may be vulnerable to cyber-attacks, cyber-security of distribution grid has not received enough attention. As smart distribution grid intensively relies on communication infrastructures, the authors assume in this study that an attacker can compromise the communication and successfully conduct attacks against crucial functions of the distribution management system, making the distribution system prone to instability boundaries for collapses. They formulate the attack detection problem in the distribution grid as a statistical learning problem and demonstrate a comprehensive benchmark of statistical learning methods on various IEEE distribution test systems. The proposed learning algorithms are tested using various attack scenarios which include distinct features of modern distribution grid such as integration of DERs and EVs. Furthermore, the interaction between transmission and distribution systems and its effect on the attack detection problem are investigated. Simulation results show attack detection is more challenging in the distribution grid.

UR - http://www.scopus.com/inward/record.url?scp=85065231034&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85065231034&partnerID=8YFLogxK

U2 - 10.1049/iet-gtd.2018.6801

DO - 10.1049/iet-gtd.2018.6801

M3 - Article

AN - SCOPUS:85065231034

VL - 13

SP - 1441

EP - 1455

JO - IET Generation, Transmission and Distribution

JF - IET Generation, Transmission and Distribution

SN - 1751-8687

IS - 8

ER -