kth.sePublications
Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
A Reinforcement Learning Approach to Undetectable Attacks Against Automatic Generation Control
KTH, School of Electrical Engineering and Computer Science (EECS), Computer Science, Network and Systems Engineering.ORCID iD: 0000-0002-9988-9545
KTH, School of Electrical Engineering and Computer Science (EECS), Computer Science, Network and Systems Engineering.ORCID iD: 0000-0002-1958-5446
KTH, School of Electrical Engineering and Computer Science (EECS), Computer Science, Network and Systems Engineering.ORCID iD: 0000-0002-4876-0223
2024 (English)In: IEEE Transactions on Smart Grid, ISSN 1949-3053, E-ISSN 1949-3061, Vol. 15, no 1, p. 959-972Article in journal (Refereed) Published
Abstract [en]

Automatic generation control (AGC) is an essential functionality for ensuring the stability of power systems, and its secure operation is thus of utmost importance to power system operators. In this paper, we investigate the vulnerability of AGC to false data injection attacks that could remain undetected by traditional detection methods based on the area control error (ACE) and the recently proposed unknown input observer (UIO). We formulate the problem of computing undetectable attacks as a multi-objective partially observable Markov decision process. We propose a flexible reward function that allows to explore the trade-off between attack impact and detectability, and use the proximal policy optimization (PPO) algorithm for learning efficient attack policies. Through extensive simulations of a 3-area power system, we show that the proposed attacks can drive the frequency beyond critical limits, while remaining undetectable by state-of-the-art algorithms employed for fault and attack detection in AGC. Our results also show that detectors trained using supervised and unsupervised machine learning can both significantly outperform existing detectors.

Place, publisher, year, edition, pages
Institute of Electrical and Electronics Engineers (IEEE) , 2024. Vol. 15, no 1, p. 959-972
Keywords [en]
Automatic generation control, reinforcement learning, false data injection attack, power system security, unknown input observer, partially observable Markov decision process
National Category
Control Engineering
Identifiers
URN: urn:nbn:se:kth:diva-345054DOI: 10.1109/TSG.2023.3288676ISI: 001132788800056Scopus ID: 2-s2.0-85181397483OAI: oai:DiVA.org:kth-345054DiVA, id: diva2:1849231
Note

QC 20240405

Available from: 2024-04-05 Created: 2024-04-05 Last updated: 2024-04-05Bibliographically approved

Open Access in DiVA

No full text in DiVA

Other links

Publisher's full textScopus

Authority records

Shereen, EzzeldinKazari, KiarashDán, György

Search in DiVA

By author/editor
Shereen, EzzeldinKazari, KiarashDán, György
By organisation
Network and Systems Engineering
In the same journal
IEEE Transactions on Smart Grid
Control Engineering

Search outside of DiVA

GoogleGoogle Scholar

doi
urn-nbn

Altmetric score

doi
urn-nbn
Total: 50 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf