Abstract
In the process of the detection of a false data injection attack (FDIA) in power systems, there are problems of complex data features and low detection accuracy. From the perspective of the correlation and redundancy of the essential characteristics of the attack data, a detection method of the FDIA in smart grids based on cyber-physical genes is proposed. Firstly, the principle and characteristics of the FDIA are analyzed, and the concept of the cyber-physical FDIA gene is defined. Considering the non-functional dependency and nonlinear correlation of cyber-physical data in power systems, the optimal attack gene feature set of the maximum mutual information coefficient is selected. Secondly, an unsupervised pre-training encoder is set to extract the cyber-physical attack gene. Combined with the supervised fine-tuning classifier to train and update the network parameters, the FDIA detection model with stacked autoencoder network is constructed. Finally, a self-adaptive cuckoo search algorithm is designed to optimize the model parameters, and a novel attack detection method is proposed. The analysis of case studies shows that the proposed method can effectively improve the detection accuracy and effect of the FDIA on cyber-physical power systems.
Highlights
With the continuous development of information technology, the interaction between information flow and energy flow in power systems is becoming more and more frequent (Yu and Xue, 2016; Xu et al, 2018; Qu et al, 2019)
The analysis of case studies shows that the proposed method can effectively improve the detection accuracy and effect of the false data injection attack (FDIA) on cyber-physical power systems
According to the consideration of the complex characteristics of the cyber-physical power systems (CPPS) data, this paper proposes a method for identifying the FDIA in the CPPS based on cyber-physical genes
Summary
With the continuous development of information technology, the interaction between information flow and energy flow in power systems is becoming more and more frequent (Yu and Xue, 2016; Xu et al, 2018; Qu et al, 2019). The detection model uses the cyber-physical optimal attack gene feature set after the above feature selection method as the input layer, and the type of attack on the system is used as the output layer of the neural network. A self-adaptive cuckoo search (SACS) algorithm is proposed to optimize the initial parameters of the SAE model On this basis, a new method of FDIA detection in the CPPS based on SACS-SAE is obtained. Step (2) After obtaining the standardized data set, use the maximum information coefficient to calculate the correlation between the feature and the category, and the redundancy between the feature and the category, and screen the optimal cyber-physical attack gene feature set based on the maximum mutual information coefficient.
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
