Опубликована: Июнь 21, 2024
Язык: Английский
Опубликована: Июнь 21, 2024
Язык: Английский
Electric Power Systems Research, Год журнала: 2024, Номер 233, С. 110509 - 110509
Опубликована: Май 25, 2024
Язык: Английский
Процитировано
11SN Computer Science, Год журнала: 2025, Номер 6(1)
Опубликована: Янв. 7, 2025
Язык: Английский
Процитировано
2Опубликована: Янв. 1, 2024
Язык: Английский
Процитировано
7Results in Engineering, Год журнала: 2025, Номер unknown, С. 105042 - 105042
Опубликована: Апрель 1, 2025
Язык: Английский
Процитировано
1Sustainable Energy Technologies and Assessments, Год журнала: 2024, Номер 64, С. 103682 - 103682
Опубликована: Фев. 29, 2024
Язык: Английский
Процитировано
3Knowledge-Based Systems, Год журнала: 2024, Номер 301, С. 112211 - 112211
Опубликована: Июль 14, 2024
Язык: Английский
Процитировано
3Applied Sciences, Год журнала: 2024, Номер 14(16), С. 6865 - 6865
Опубликована: Авг. 6, 2024
As the informatization of power systems advances, secure operation faces various potential network attacks and threats. The false data injection attack (FDIA) is a common mode that can lead to abnormal system operations serious economic losses by injecting into terminal links or devices. current research on FDIA primarily focuses detecting its existence, but there relatively little localization attacks. To address this challenge, study proposes novel method (GA-CNN-LSTM) combines convolutional neural networks (CNNs), long short-term memory (LSTM), genetic algorithm (GA) accurately locate attacked bus line. This utilizes CNN extract local features LSTM with time series information global features. It integrates deeply explore complex patterns dynamic changes in data, effectively optimize hyperparameters using GA ensure an optimal performance model. Simulation experiments were conducted IEEE 14-bus 118-bus test systems. results indicate GA-CNN-LSTM achieved F1 scores for location identification 99.71% 99.10%, respectively, demonstrating superior compared other methods.
Язык: Английский
Процитировано
3Computers & Security, Год журнала: 2025, Номер unknown, С. 104320 - 104320
Опубликована: Янв. 1, 2025
Язык: Английский
Процитировано
0Computation, Год журнала: 2025, Номер 13(2), С. 33 - 33
Опубликована: Фев. 1, 2025
The integration of solar Photovoltaic (PV) systems into the AC grid poses stability challenges, especially with increasing inverter-based resources. For an efficient operation system, smart grid-forming inverters need to communicate Supervisory Control and Data Acquisition (SCADA) system. However, Internet-of-Things devices that SCADA make these vulnerable. Though many researchers proposed Artificial-Intelligence-based detection strategies, identification location attack is not considered by strategies. To overcome this drawback, paper proposes a novel Convolution extreme gradient boosting (ConvXGBoost) method for only detecting Denial Service (DoS) False Injection (FDI) attacks but also identifying component system was compromised. model compared existing Neural Network (CNN) decision tree (DT) Simulation results demonstrate effectiveness both PV fuel cell (PV-FC) systems. example, accuracy 99.25% 97.76% CNN 99.12% DT during DoS on Moreover, can detect identify faster than other models.
Язык: Английский
Процитировано
0Engineering Applications of Artificial Intelligence, Год журнала: 2025, Номер 148, С. 110374 - 110374
Опубликована: Март 5, 2025
Язык: Английский
Процитировано
0