Detection of False Data Injection Attacks on Load Frequency Control System with Renewable Energy Based on Fuzzy Logic and Neural Networks

Abstract

Load frequency control (LFC) system may be destroyed by false data injection attacks (FDIAs) and consequently the security of the power system will be impacted. High-efficiency FDIA detection can reduce the damage and power loss to the power system. This paper defines various typical and hybrid FDIAs, and the influence of several FDIAs with different characteristics on the multi-area LFC system is analyzed. To detect various attacks, we introduce an improved data-driven method, which consists of fuzzy logic and neural networks. Fuzzy logic has the features of high applicability, robustness, and agility, which can make full use of samples. Further, we construct the LFC system on MATLAB/Simulink platform, and systematically simulate the experiments that FDIAs affect the LFC system by tampering with measurement data. Among them, considering the large-scale penetration of renewable energy with intermittency and volatility, we generate three simulation scenarios with or without renewable energy generation. Then, the performance for detecting FDIAs of the improved method is verified by simulation data samples.

A Reinforcement Learning Approach to Undetectable Attacks Against Automatic Generation Control

“…= 300 MW, and the maximum allowed deviation of the frequency (in the case frequency measurements are attacked) is a ω+ = 0.006 p.u. = 0.36 Hz, as in (18). The aforementioned values were chosen based on preliminary experiments s.t.…”

“…A multilayer perceptron (MLP) combined with feature selection was trained in [17] to distinguish between attacked and non-attacked ACE signals. Recently, [18] proposed a combination of fuzzy logic and neural networks for the detection of FDIAs, where the input data consisted of the ACE values as well as other measurements.…”

“…where a P + and a ω+ denote the respective maximum allowed attack magnitudes. The reason for constraint (18) is that an attack that sets the power-flow or frequency measurements too far from their expected values should be easily detectable. Moreover, the attacker is constrained by that N i=1 ∆P tie i,a and N i=1 a P i must be kept close to zero for any attack.…”

Detection and Defense Method Against False Data Injection Attacks for Distributed Load Frequency Control System in Microgrid

“…Reference [31] suggests an observerbased control strategy for resisting FDIAs. Reference [32] proposes a method that combines fuzzy logic and neural network to detect multiple FDIAs. Reference [33] develops an LFC method based on a dynamic output feedback controller.…”