Mitigating False Data Injection Attacks in DC Microgrids with Multiple Interlinking Converters

The coordination among Multiple Interlinking Converters (MICs) is facilitated through a low-bandwidth, neighborhood communication-assisted, distributed cooperative control strategy. However, these systems are vulnerable to False Data Injection Attacks (FDIAs), which create significant challenges by maliciously falsifying communication signals, disrupting the coordination of MICs, and potentially rendering the entire microgrid inoperable. To address this threat, this paper proposes a signal estimation stategy based on the Adaptive Neuro-Fuzzy Inference System (ANFIS) to mitigate FDIAs in MICs within clustered DC microgrids. During the offline training phase, the ANFIS-based estimator is developed using the local voltage measurements from each bidirectional interlinking converter as inputs and the sum of communicated signals entering each converter as the output. For the online stage, a reference tracking approach is developed to restore the attacked signals using the estimated values from ANFIS, effectively mitigating the impact of FDIA. Through extensive simulations, we demonstrate the effectiveness of our proposed approach in handling various FDIAs, including time-varying attack signals and unbounded attacks.