Codesign of FDI Attacks Detection, Isolation, and Mitigation for Complex Microgrid Systems: An HBF-NN-Based Approach

Area of Science:

• Electrical Engineering
• Control Systems
• Cybersecurity

Background:

• Microgrid systems are increasingly complex, integrating electric vehicles (EVs) and renewable energy sources.
• These systems are vulnerable to false data injection (FDI) attacks, threatening operational stability.
• Existing security measures may not adequately address the dynamic nature of modern microgrids.

Purpose of the Study:

• To design an intelligent scheme for detecting, isolating, and mitigating FDI attacks in networked microgrids with EVs.
• To develop a robust system capable of operating reliably in insecure network environments.
• To enhance the resilience of microgrids against sophisticated cyber threats.

Main Methods:

• A networked microgrid model with EVs was established, incorporating load disturbances, wind fluctuations, and FDI attacks.
• An intelligent hyper basis function neural network (HBF-NN) observer was designed for state estimation and online attack signal reconstruction.
• A novel HBF-NN-based H_∞ controller was developed for online mitigation of FDI attack impacts.

Main Results:

• The HBF-NN observer accurately estimated microgrid states and identified FDI signals in real-time.
• The HBF-NN-based H_∞ controller effectively mitigated the negative effects of FDI attacks.
• Simulations demonstrated the feasibility and superiority of the proposed two-stage integrated detection and mitigation algorithm.

Conclusions:

• The developed intelligent scheme provides a robust solution for FDI attack defense in complex microgrids with EVs.
• The proposed methodology enhances the security and reliability of microgrid operations under cyber-attack conditions.
• This research contributes to securing critical energy infrastructure against evolving cyber threats.