Network Attack Detection Method of the Cyber-Physical Power System Based on Ensemble Learning
With the rapid development of power grid informatization, the power system has evolved into a multi-dimensional heterogeneous complex system with high cyber-physical integration, denoting the Cyber-Physical Power System (CPPS). Network attack, in addition to faults, becomes an important factor restr...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-06-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/12/13/6498 |
| _version_ | 1797480968003518464 |
|---|---|
| author | Jie Cao Da Wang Qi-Ming Wang Xing-Liang Yuan Kai Wang Chin-Ling Chen |
| author_facet | Jie Cao Da Wang Qi-Ming Wang Xing-Liang Yuan Kai Wang Chin-Ling Chen |
| author_sort | Jie Cao |
| collection | DOAJ |
| description | With the rapid development of power grid informatization, the power system has evolved into a multi-dimensional heterogeneous complex system with high cyber-physical integration, denoting the Cyber-Physical Power System (CPPS). Network attack, in addition to faults, becomes an important factor restricting the stable operation of the power system. Under the influence of network attacks, to improve the operational stability of CPPSs, this paper proposes a CPPS network attack detection method based on ensemble learning. First, to solve the shortcomings of a low detection precision caused by insufficient network attack samples, a power data balancing processing method was proposed. Then, the LightGBM ensemble was constructed to detect network attack events and lock the fault points caused by the attack. At the same time, in the process of gradient boost, the focal loss was introduced to optimize the attention weight of the classifier to the misclassified samples, thus improving the network attack detection precision. Finally, we propose an effective evaluation method of the network attack detection model based on cyber-physical comprehensive consideration. In addition, the cyber-physical power system stability under the action of the network attack detection model is quantitatively analyzed. The experimental results show that the F1 score of network attack detection increases by 16.73%, and the precision increases by 15.67%. |
| first_indexed | 2024-03-09T22:07:48Z |
| format | Article |
| id | doaj.art-b7b5bec14a874ab698821d6338e48c97 |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-09T22:07:48Z |
| publishDate | 2022-06-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-b7b5bec14a874ab698821d6338e48c972023-11-23T19:37:43ZengMDPI AGApplied Sciences2076-34172022-06-011213649810.3390/app12136498Network Attack Detection Method of the Cyber-Physical Power System Based on Ensemble LearningJie Cao0Da Wang1Qi-Ming Wang2Xing-Liang Yuan3Kai Wang4Chin-Ling Chen5School of Computer Science, Northeast Electric Power University, Jilin 132012, ChinaSchool of Electrical Engineering, Northeast Electric Power University, Jilin 132012, ChinaSchool of Computer Science, Northeast Electric Power University, Jilin 132012, ChinaSchool of Computer Science, Northeast Electric Power University, Jilin 132012, ChinaMaterial Company of State Grid Jilin Electric Power Co., Ltd., Changchun 130000, ChinaSchool of Information Engineering, Changchun Sci-Tech University, Changchun 130600, ChinaWith the rapid development of power grid informatization, the power system has evolved into a multi-dimensional heterogeneous complex system with high cyber-physical integration, denoting the Cyber-Physical Power System (CPPS). Network attack, in addition to faults, becomes an important factor restricting the stable operation of the power system. Under the influence of network attacks, to improve the operational stability of CPPSs, this paper proposes a CPPS network attack detection method based on ensemble learning. First, to solve the shortcomings of a low detection precision caused by insufficient network attack samples, a power data balancing processing method was proposed. Then, the LightGBM ensemble was constructed to detect network attack events and lock the fault points caused by the attack. At the same time, in the process of gradient boost, the focal loss was introduced to optimize the attention weight of the classifier to the misclassified samples, thus improving the network attack detection precision. Finally, we propose an effective evaluation method of the network attack detection model based on cyber-physical comprehensive consideration. In addition, the cyber-physical power system stability under the action of the network attack detection model is quantitatively analyzed. The experimental results show that the F1 score of network attack detection increases by 16.73%, and the precision increases by 15.67%.https://www.mdpi.com/2076-3417/12/13/6498CPPSnetwork attack detectionensemble learningLightGBMreliability evaluation |
| spellingShingle | Jie Cao Da Wang Qi-Ming Wang Xing-Liang Yuan Kai Wang Chin-Ling Chen Network Attack Detection Method of the Cyber-Physical Power System Based on Ensemble Learning Applied Sciences CPPS network attack detection ensemble learning LightGBM reliability evaluation |
| title | Network Attack Detection Method of the Cyber-Physical Power System Based on Ensemble Learning |
| title_full | Network Attack Detection Method of the Cyber-Physical Power System Based on Ensemble Learning |
| title_fullStr | Network Attack Detection Method of the Cyber-Physical Power System Based on Ensemble Learning |
| title_full_unstemmed | Network Attack Detection Method of the Cyber-Physical Power System Based on Ensemble Learning |
| title_short | Network Attack Detection Method of the Cyber-Physical Power System Based on Ensemble Learning |
| title_sort | network attack detection method of the cyber physical power system based on ensemble learning |
| topic | CPPS network attack detection ensemble learning LightGBM reliability evaluation |
| url | https://www.mdpi.com/2076-3417/12/13/6498 |
| work_keys_str_mv | AT jiecao networkattackdetectionmethodofthecyberphysicalpowersystembasedonensemblelearning AT dawang networkattackdetectionmethodofthecyberphysicalpowersystembasedonensemblelearning AT qimingwang networkattackdetectionmethodofthecyberphysicalpowersystembasedonensemblelearning AT xingliangyuan networkattackdetectionmethodofthecyberphysicalpowersystembasedonensemblelearning AT kaiwang networkattackdetectionmethodofthecyberphysicalpowersystembasedonensemblelearning AT chinlingchen networkattackdetectionmethodofthecyberphysicalpowersystembasedonensemblelearning |