The Method for smart grid false data injection attack detection based on multilevel fingerprint identity authentication

Abstract

Abstract With the rapid development of Cyber-Physical Systems (CPS), security concerns have increasingly garnered attention. This paper focuses on the security threats faced by smart grid systems, particularly false data injection (FDI) attacks, and proposes a multilevel fingerprint identity authentication method to provide effective security for the operation of smart grids. Firstly, we construct a mathematical model of the smart grid by using harmonics and direct current attenuation components to establish a foundation for subsequent feature extraction and matching authentication. Secondly, a multi-granularity feature approach is utilized to represent the model in multiple levels and extract feature information granularity, thereby enhancing the system’s ability to detect attack signals. In addition, we employ the gap measurement method to perform multi-scale matching of the granularity information of sensor data with that of the data security repository, to detect attack signals. Finally, experimental results confirm that this method effectively detects FDI attacks, improves detection accuracy while ensuring real-time detection, and realizes the safe and reliable operation of smart grid systems.