Detection of Data Integrity Attack Using Model and Data-Driven-Based Approach in CPPS
The cyber-physical power system (CPPS) is a modern infrastructure utilising information and communication technology that has become more vulnerable to cyberattacks in recent years. The attack magnitude injected by the adversary is stealthier and it cannot be detected using conventional bad data det...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2023-01-01
|
| Series: | International Transactions on Electrical Energy Systems |
| Online Access: | http://dx.doi.org/10.1155/2023/6098519 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832558483138936832 |
|---|---|
| author | G. Y. Sree Varshini S. Latha |
| author_facet | G. Y. Sree Varshini S. Latha |
| author_sort | G. Y. Sree Varshini |
| collection | DOAJ |
| description | The cyber-physical power system (CPPS) is a modern infrastructure utilising information and communication technology that has become more vulnerable to cyberattacks in recent years. The attack magnitude injected by the adversary is stealthier and it cannot be detected using conventional bad data detection techniques. Protecting sensitive data from data integrity attacks (DIA) is essential for ensuring system security and reliability. A tragic event will occur if the attack goes unreported. Therefore, DIA detection is highly vital for the operator in the control centre to make important decisions. This paper addresses the attack impact on WAC applications and attack detection using the model-based method and data-driven-based methods. On the basis of the validation of performance indicators, various detection approaches are simulated and compared to determine the best detection strategy. Simulation results show that in the model-based anomaly detection method, the recursive polynomial model estimator (RPME) has better detection performance than the recursive least square estimator (RLSE). The convolutional neural network- (CNN-) based data-driven anomaly detection technique outperforms other machine learning (ML) techniques such as support vector machine (SVM), K-nearest neighbour (KNN), and random forest (RF). On the WSCC 3 machine 9-bus system, the efficacy of the suggested methods is evaluated. |
| format | Article |
| id | doaj-art-d67c59bed2e349ac9c5ac350d109eae1 |
| institution | Kabale University |
| issn | 2050-7038 |
| language | English |
| publishDate | 2023-01-01 |
| publisher | Wiley |
| record_format | Article |
| series | International Transactions on Electrical Energy Systems |
| spelling | doaj-art-d67c59bed2e349ac9c5ac350d109eae12025-02-03T01:32:19ZengWileyInternational Transactions on Electrical Energy Systems2050-70382023-01-01202310.1155/2023/6098519Detection of Data Integrity Attack Using Model and Data-Driven-Based Approach in CPPSG. Y. Sree Varshini0S. Latha1Thiagarajar College of EngineeringThiagarajar College of EngineeringThe cyber-physical power system (CPPS) is a modern infrastructure utilising information and communication technology that has become more vulnerable to cyberattacks in recent years. The attack magnitude injected by the adversary is stealthier and it cannot be detected using conventional bad data detection techniques. Protecting sensitive data from data integrity attacks (DIA) is essential for ensuring system security and reliability. A tragic event will occur if the attack goes unreported. Therefore, DIA detection is highly vital for the operator in the control centre to make important decisions. This paper addresses the attack impact on WAC applications and attack detection using the model-based method and data-driven-based methods. On the basis of the validation of performance indicators, various detection approaches are simulated and compared to determine the best detection strategy. Simulation results show that in the model-based anomaly detection method, the recursive polynomial model estimator (RPME) has better detection performance than the recursive least square estimator (RLSE). The convolutional neural network- (CNN-) based data-driven anomaly detection technique outperforms other machine learning (ML) techniques such as support vector machine (SVM), K-nearest neighbour (KNN), and random forest (RF). On the WSCC 3 machine 9-bus system, the efficacy of the suggested methods is evaluated.http://dx.doi.org/10.1155/2023/6098519 |
| spellingShingle | G. Y. Sree Varshini S. Latha Detection of Data Integrity Attack Using Model and Data-Driven-Based Approach in CPPS International Transactions on Electrical Energy Systems |
| title | Detection of Data Integrity Attack Using Model and Data-Driven-Based Approach in CPPS |
| title_full | Detection of Data Integrity Attack Using Model and Data-Driven-Based Approach in CPPS |
| title_fullStr | Detection of Data Integrity Attack Using Model and Data-Driven-Based Approach in CPPS |
| title_full_unstemmed | Detection of Data Integrity Attack Using Model and Data-Driven-Based Approach in CPPS |
| title_short | Detection of Data Integrity Attack Using Model and Data-Driven-Based Approach in CPPS |
| title_sort | detection of data integrity attack using model and data driven based approach in cpps |
| url | http://dx.doi.org/10.1155/2023/6098519 |
| work_keys_str_mv | AT gysreevarshini detectionofdataintegrityattackusingmodelanddatadrivenbasedapproachincpps AT slatha detectionofdataintegrityattackusingmodelanddatadrivenbasedapproachincpps |