Paper Info
Title
Abnormal flow detection in industrial control network based on deep reinforcement learning
Abstract
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. (C) 2021 Published by Elsevier Inc.
Year
DOI
Venue
2021
10.1016/j.amc.2021.126379
APPLIED MATHEMATICS AND COMPUTATION
Keywords
DocType
Volume
Deep reinforcement learning, Industrial control systems, Abnormal flow detection, The learning strategy
Journal
409
ISSN
Citations 
PageRank 
0096-3003
0
0.34
References 
Authors
0
10
Name
Order
Citations
PageRank
Wang Weiping133563.84
Junjiang Guo200.34
Zhen Wang3106085.86
Hao Wang400.34
Jun Cheng500.68
Chunyang Wang6137.27
Manman Yuan7133.55
Jürgen Kurths82000142.58
Xiong Luo901.35
Yang Gao1000.68