Graph Neural Network-Based Approach for Detecting False Data Injection Attacks on Voltage Stability
The integration of information and communication technologies into modern power systems has contributed to enhanced efficiency, controllability, and voltage regulation. Concurrently, these technologies expose power systems to cyberattacks, which could lead to voltage instability and significant dama...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Open Access Journal of Power and Energy |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10824826/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832583957623865344 |
|---|---|
| author | Shahriar Rahman Fahim Rachad Atat Cihat Kececi Abdulrahman Takiddin Muhammad Ismail Katherine R. Davis Erchin Serpedin |
| author_facet | Shahriar Rahman Fahim Rachad Atat Cihat Kececi Abdulrahman Takiddin Muhammad Ismail Katherine R. Davis Erchin Serpedin |
| author_sort | Shahriar Rahman Fahim |
| collection | DOAJ |
| description | The integration of information and communication technologies into modern power systems has contributed to enhanced efficiency, controllability, and voltage regulation. Concurrently, these technologies expose power systems to cyberattacks, which could lead to voltage instability and significant damage. Traditional false data injection attacks (FDIAs) detectors are inadequate in addressing cyberattacks on voltage regulation since a) they overlook such attacks within power grids and b) primarily rely on static thresholds and simple anomaly detection techniques, which cannot capture the complex interplay between voltage stability, cyberattacks, and defensive actions. To address the aforementioned challenges, this paper develops an FDIA detection approach that considers data falsification attacks on voltage regulation and enhances the voltage stability index. A graph autoencoder-based detector that is able to identify cyberattacks targeting voltage regulation is proposed. A bi-level optimization approach is put forward to concurrently optimize the objectives of both attackers and defenders in the context of voltage regulation. The proposed detector underwent rigorous training and testing across different kinds of attacks, demonstrating enhanced generalization performance in all situations. Simulations were performed on the Iberian power system topology, featuring 486 buses. The proposed model achieves 98.11% average detection rate, which represents a significant enhancement of 10-25% compared to the cutting-edge detectors. This provides strong evidence for the effectiveness of proposed strategy in tackling cyberattacks on voltage regulation. |
| format | Article |
| id | doaj-art-0777ab3aaba449c3a21f51feabf0b528 |
| institution | Kabale University |
| issn | 2687-7910 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Open Access Journal of Power and Energy |
| spelling | doaj-art-0777ab3aaba449c3a21f51feabf0b5282025-01-28T00:02:14ZengIEEEIEEE Open Access Journal of Power and Energy2687-79102025-01-0112122310.1109/OAJPE.2024.352426810824826Graph Neural Network-Based Approach for Detecting False Data Injection Attacks on Voltage StabilityShahriar Rahman Fahim0https://orcid.org/0000-0001-9185-4658Rachad Atat1https://orcid.org/0000-0001-8075-6243Cihat Kececi2https://orcid.org/0000-0002-2097-5855Abdulrahman Takiddin3https://orcid.org/0000-0003-4793-003XMuhammad Ismail4https://orcid.org/0000-0002-8051-9747Katherine R. Davis5https://orcid.org/0000-0002-1603-1122Erchin Serpedin6https://orcid.org/0000-0001-9069-770XElectrical and Computer Engineering Department, Texas A&M University, College Station, TX, USADepartment of Computer Science and Mathematics, Lebanese American University, Beirut, LebanonElectrical and Computer Engineering Department, Texas A&M University, College Station, TX, USADepartment of Electrical and Computer Engineering, Florida State University, Tallahassee, FL, USADepartment of Computer Science, Tennessee Tech University, Cookeville, TN, USAElectrical and Computer Engineering Department, Texas A&M University, College Station, TX, USAElectrical and Computer Engineering Department, Texas A&M University, College Station, TX, USAThe integration of information and communication technologies into modern power systems has contributed to enhanced efficiency, controllability, and voltage regulation. Concurrently, these technologies expose power systems to cyberattacks, which could lead to voltage instability and significant damage. Traditional false data injection attacks (FDIAs) detectors are inadequate in addressing cyberattacks on voltage regulation since a) they overlook such attacks within power grids and b) primarily rely on static thresholds and simple anomaly detection techniques, which cannot capture the complex interplay between voltage stability, cyberattacks, and defensive actions. To address the aforementioned challenges, this paper develops an FDIA detection approach that considers data falsification attacks on voltage regulation and enhances the voltage stability index. A graph autoencoder-based detector that is able to identify cyberattacks targeting voltage regulation is proposed. A bi-level optimization approach is put forward to concurrently optimize the objectives of both attackers and defenders in the context of voltage regulation. The proposed detector underwent rigorous training and testing across different kinds of attacks, demonstrating enhanced generalization performance in all situations. Simulations were performed on the Iberian power system topology, featuring 486 buses. The proposed model achieves 98.11% average detection rate, which represents a significant enhancement of 10-25% compared to the cutting-edge detectors. This provides strong evidence for the effectiveness of proposed strategy in tackling cyberattacks on voltage regulation.https://ieeexplore.ieee.org/document/10824826/Cybersecurityvoltage regulationgraph autoencodervoltage stabilityfalse data injection attacksbad data intrusion |
| spellingShingle | Shahriar Rahman Fahim Rachad Atat Cihat Kececi Abdulrahman Takiddin Muhammad Ismail Katherine R. Davis Erchin Serpedin Graph Neural Network-Based Approach for Detecting False Data Injection Attacks on Voltage Stability IEEE Open Access Journal of Power and Energy Cybersecurity voltage regulation graph autoencoder voltage stability false data injection attacks bad data intrusion |
| title | Graph Neural Network-Based Approach for Detecting False Data Injection Attacks on Voltage Stability |
| title_full | Graph Neural Network-Based Approach for Detecting False Data Injection Attacks on Voltage Stability |
| title_fullStr | Graph Neural Network-Based Approach for Detecting False Data Injection Attacks on Voltage Stability |
| title_full_unstemmed | Graph Neural Network-Based Approach for Detecting False Data Injection Attacks on Voltage Stability |
| title_short | Graph Neural Network-Based Approach for Detecting False Data Injection Attacks on Voltage Stability |
| title_sort | graph neural network based approach for detecting false data injection attacks on voltage stability |
| topic | Cybersecurity voltage regulation graph autoencoder voltage stability false data injection attacks bad data intrusion |
| url | https://ieeexplore.ieee.org/document/10824826/ |
| work_keys_str_mv | AT shahriarrahmanfahim graphneuralnetworkbasedapproachfordetectingfalsedatainjectionattacksonvoltagestability AT rachadatat graphneuralnetworkbasedapproachfordetectingfalsedatainjectionattacksonvoltagestability AT cihatkececi graphneuralnetworkbasedapproachfordetectingfalsedatainjectionattacksonvoltagestability AT abdulrahmantakiddin graphneuralnetworkbasedapproachfordetectingfalsedatainjectionattacksonvoltagestability AT muhammadismail graphneuralnetworkbasedapproachfordetectingfalsedatainjectionattacksonvoltagestability AT katherinerdavis graphneuralnetworkbasedapproachfordetectingfalsedatainjectionattacksonvoltagestability AT erchinserpedin graphneuralnetworkbasedapproachfordetectingfalsedatainjectionattacksonvoltagestability |