Deutsch
 
Datenschutzhinweis Impressum
  DetailsucheBrowse

Datensatz

DATENSATZ AKTIONENEXPORT
Zur Ablage hinzufügen
  Lokale TagsFreigabegeschichteDetailsÜbersicht

Freigegeben
Zeitschriftenartikel

Abnormal flow detection in industrial control network based on deep reinforcement learning

Urheber*innen

Wang,  Weiping
External Organizations;

Guo,  Junjiang
External Organizations;

Wang,  Zhen
External Organizations;

Wang,  Hao
External Organizations;

Cheng,  Jun
External Organizations;

Wang,  Chunyang
External Organizations;

Yuan,  Manman
External Organizations;

/persons/resource/Juergen.Kurths

Kurths,  Jürgen
Potsdam Institute for Climate Impact Research;

Luo,  Xiong
External Organizations;

Gao,  Yang
External Organizations;

Externe Ressourcen
Es sind keine externen Ressourcen hinterlegt
Volltexte (frei zugänglich)
Es sind keine frei zugänglichen Volltexte in PIKpublic verfügbar
Ergänzendes Material (frei zugänglich)
Es sind keine frei zugänglichen Ergänzenden Materialien verfügbar
Zitation

Wang, W., Guo, J., Wang, Z., Wang, H., Cheng, J., Wang, C., Yuan, M., Kurths, J., Luo, X., Gao, Y. (2021): Abnormal flow detection in industrial control network based on deep reinforcement learning. - Applied Mathematics and Computation, 409, 126379.
https://doi.org/10.1016/j.amc.2021.126379


Zitierlink: https://publications.pik-potsdam.de/pubman/item/item_26268
Zusammenfassung
Industrial control systems are the brain and central nervous system of a country’s vital infrastructure. Once the control system collapses, the consequences are unimaginable. Therefore, the safety of industrial control system has become the top priority in the field of safety. Aiming at the problem that the traditional abnormal flow detection model in the industrial control system is not accurate in identifying abnormalities, we combine the perception ability of deep learning with the decision-making ability of reinforcement learning, and propose an abnormal flow detection model based on deep reinforcement learning. The neural network is used to extract the features of the preprocessed dataset, and then the learning strategy can be adjusted according to the special advantages of strengthening the decision-making ability of learning and feedback. The experimental results show that the model based on deep reinforcement learning can achieve 98.06% accuracy in abnormal flow detection.Compared with various methods proposed by peers in current literature, this method is superior to other technologies in four evaluation indexes including accuracy rate, accuracy rate, recall rate and F1 score, among which the accuracy is increased by 2 percentage points.