Open AccessResearch on Fake Data Injection Attack Detection in Intelligent Ship Power System
Author(s) -
Ganlong Wang,
Junfeng Zhu
Publication year - 2020
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1607/1/012129
Subject(s) - electric power system , computer science , power grid , perspective (graphical) , computer security , point (geometry) , index (typography) , power (physics) , data mining , artificial intelligence , physics , geometry , mathematics , quantum mechanics , world wide web
The application of computers in marine power systems is becoming more and more extensive, and the network security of marine power systems has become an important part. This paper studies the false data injection attack (FDIA) of the ship’s power information physical system. First, it analyzes the objectives and principles of the FDIA attack from the perspective of the attacker and the possible consequences on the power grid. From the technical point of view, it studies two aspects of FDIA attacks, analyzes and summarizes various methods in detection and defense. The FDIA defense model based on deep learning is proposed, and on this basis, the measurement points that need to be protected are confirmed according to the importance index I k . And its index is applied to the established fake data injection attack detection model based on deep learning, and the accuracy of the two traditional fake data injection attacks is compared. Experiments show that the accuracy of this model is increased to more than 90% compared with traditional algorithms, which can effectively enhance the defense capability of the ship’s power system against FDIA.