| Smart Grid(SG)is a Cyber Physical System(CPS)that integrates information and communication technologies and network components to provide efficient,accurate and reliable power services.As a national key infrastructure,it is increasingly attacked by cyber attacks.How to ensure the security of smart grid networks has become a research hotspot.In recent years,False Data Injection Attack(FDIA)is one of the most threatening network attacks in smart grid cyber physics system,which can bring inestimable losses to smart grid.The attack is more secretive and offensive.It can bypass the traditional bad data detector and interfere with the accuracy of state estimation,thus making the power grid misjudge the state and causing the wrong power dispatching to lead to the paralysis of the power grid.Therefore,it is very important to study the detection method of false data injection attacks in smart grids.This paper proposes Probabilistic-based Distributed Host Collaborative Detection(P-DHCD)false data mechanism and Physical Rule-based Fuzzy Neural Network(PR-FNN)false data collaborative detection.mechanism.The main research work of this paper is as follows:Aiming at the problem that the real-time FDIA detection method in the smart grid is difficult to meet the operational control requirements and the computational cost of the control center,this paper proposes a probabilistic distributed host collaborative detection mechanism based on the characteristics of the cyber physical system.Firstly,the problem of the confidence of the participants in the collaborative voting Phasor Measurement Unit(PMU)for collaborative voting is solved.The trust-based damaged PMU identification method is designed to evaluate the overall behavior of the PMU.Then,using the physical law rules in the smart grid cyber physical system,the confidence coordination voting detection method is proposed to detect the false data.In this paper,real-time data from Powerworld is collected,and the simulation experiment is carried out in MATLAB,and the real-time detection rate of the false data injection attack can be improved by the mechanism,and the computational overhead is reduced.In order to solve the problem that it is difficult to detect false data in the future new smart grid aggregation layer architecture,a cooperative detection mechanism of false data based on physical rules-fuzzy neural network is proposed in this paper.Firstly,elliptic curve cryptosystem is used to encrypt the measured values at the communication layer and the physical layer to prevent tampering with the measured values during wireless network transmission without interfering with the results of PMU data detection.Then the identity authentication(LSA)algorithm based on logical scheduling is used to ensure the identity legitimacy of the local aggregator as the detector and the controller.Finally,based on the physical rule-fuzzy neural network false data detection method,it is detected whether the data in the physical layer PMU is tampered with.In this paper,MATLAB verifies that the mechanism can effectively detect false data. |
