Detection and diagnosis of unknown threats in power equipment using machine learning and Spark technology
With the continuous advancement of network technology, attack behaviors have become increasingly diversified, giving rise to new challenges in threat detection. To effectively monitor and diagnose unknown threats, we have created an unknown threat detection model for power equipment based on Spark t...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
AIP Publishing LLC
2025-01-01
|
| Series: | AIP Advances |
| Online Access: | http://dx.doi.org/10.1063/5.0191442 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832542723792437248 |
|---|---|
| author | Li Di Cen Chen Zhuo Lv Mingyan Li Nuannuan Li Hao Chang |
| author_facet | Li Di Cen Chen Zhuo Lv Mingyan Li Nuannuan Li Hao Chang |
| author_sort | Li Di |
| collection | DOAJ |
| description | With the continuous advancement of network technology, attack behaviors have become increasingly diversified, giving rise to new challenges in threat detection. To effectively monitor and diagnose unknown threats, we have created an unknown threat detection model for power equipment based on Spark technology. Our research utilizes a lightweight gradient-based method for detecting known threats, and we propose a novel detection approach for unknown threats that combines classical anomaly detection methods, specifically support vector machines, with autoencoders. In addition, Spark technology is employed to achieve data parallelization, enhancing detection and diagnosis efficiency. Finally, we apply stacking techniques to integrate the two detection methods, enabling hybrid intrusion detection and diagnosis. Experimental analysis indicates that the model runs in 1.88 seconds, achieving a detection accuracy of 98.88%, a precision rate of 99.06%, and a false positive rate of 2.36%. This approach allows for more efficient and accurate detection of unknown threat attacks on power grid equipment, providing robust network security for power systems. Our findings offer a new theoretical perspective for the evolving field of network security. |
| format | Article |
| id | doaj-art-74dfb688eb7d41e2a4440fdaaaad2a9a |
| institution | Kabale University |
| issn | 2158-3226 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | AIP Publishing LLC |
| record_format | Article |
| series | AIP Advances |
| spelling | doaj-art-74dfb688eb7d41e2a4440fdaaaad2a9a2025-02-03T16:40:43ZengAIP Publishing LLCAIP Advances2158-32262025-01-01151015317015317-1310.1063/5.0191442Detection and diagnosis of unknown threats in power equipment using machine learning and Spark technologyLi Di0Cen Chen1Zhuo Lv2Mingyan Li3Nuannuan Li4Hao Chang5Department of Digitalization, State Grid Henan Electric Power Company, Zhengzhou 450000, ChinaEnergy Internet Technology Research Center, State Grid Henan Electric Power Research Institute, Zhengzhou 450002, ChinaEnergy Internet Technology Research Center, State Grid Henan Electric Power Research Institute, Zhengzhou 450002, ChinaEnergy Internet Technology Research Center, State Grid Henan Electric Power Research Institute, Zhengzhou 450002, ChinaEnergy Internet Technology Research Center, State Grid Henan Electric Power Research Institute, Zhengzhou 450002, ChinaEnergy Internet Technology Research Center, State Grid Henan Electric Power Research Institute, Zhengzhou 450002, ChinaWith the continuous advancement of network technology, attack behaviors have become increasingly diversified, giving rise to new challenges in threat detection. To effectively monitor and diagnose unknown threats, we have created an unknown threat detection model for power equipment based on Spark technology. Our research utilizes a lightweight gradient-based method for detecting known threats, and we propose a novel detection approach for unknown threats that combines classical anomaly detection methods, specifically support vector machines, with autoencoders. In addition, Spark technology is employed to achieve data parallelization, enhancing detection and diagnosis efficiency. Finally, we apply stacking techniques to integrate the two detection methods, enabling hybrid intrusion detection and diagnosis. Experimental analysis indicates that the model runs in 1.88 seconds, achieving a detection accuracy of 98.88%, a precision rate of 99.06%, and a false positive rate of 2.36%. This approach allows for more efficient and accurate detection of unknown threat attacks on power grid equipment, providing robust network security for power systems. Our findings offer a new theoretical perspective for the evolving field of network security.http://dx.doi.org/10.1063/5.0191442 |
| spellingShingle | Li Di Cen Chen Zhuo Lv Mingyan Li Nuannuan Li Hao Chang Detection and diagnosis of unknown threats in power equipment using machine learning and Spark technology AIP Advances |
| title | Detection and diagnosis of unknown threats in power equipment using machine learning and Spark technology |
| title_full | Detection and diagnosis of unknown threats in power equipment using machine learning and Spark technology |
| title_fullStr | Detection and diagnosis of unknown threats in power equipment using machine learning and Spark technology |
| title_full_unstemmed | Detection and diagnosis of unknown threats in power equipment using machine learning and Spark technology |
| title_short | Detection and diagnosis of unknown threats in power equipment using machine learning and Spark technology |
| title_sort | detection and diagnosis of unknown threats in power equipment using machine learning and spark technology |
| url | http://dx.doi.org/10.1063/5.0191442 |
| work_keys_str_mv | AT lidi detectionanddiagnosisofunknownthreatsinpowerequipmentusingmachinelearningandsparktechnology AT cenchen detectionanddiagnosisofunknownthreatsinpowerequipmentusingmachinelearningandsparktechnology AT zhuolv detectionanddiagnosisofunknownthreatsinpowerequipmentusingmachinelearningandsparktechnology AT mingyanli detectionanddiagnosisofunknownthreatsinpowerequipmentusingmachinelearningandsparktechnology AT nuannuanli detectionanddiagnosisofunknownthreatsinpowerequipmentusingmachinelearningandsparktechnology AT haochang detectionanddiagnosisofunknownthreatsinpowerequipmentusingmachinelearningandsparktechnology |