Dual-hybrid intrusion detection system to detect False Data Injection in smart grids

Area of Science:

• Cybersecurity
• Power Systems Engineering
• Artificial Intelligence

Background:

• Smart grids offer benefits but increase vulnerability to cyber threats like False Data Injection Attacks (FDIAs).
• Traditional Intrusion Detection Systems (IDS) struggle to detect sophisticated FDIAs due to limitations in rule-based methods.
• There is a critical need for robust and accurate IDS tailored for smart grid environments.

Purpose of the Study:

• To propose a novel, dual-hybrid Intrusion Detection System (IDS) for enhanced detection of False Data Injection Attacks (FDIAs) in smart grids.
• To improve the accuracy, robustness, and efficiency of smart grid cybersecurity measures against advanced cyber threats.
• To address the limitations of existing IDS by integrating advanced feature selection and deep learning techniques.

Main Methods:

• Implemented a hybrid feature selection approach combining Particle Swarm Optimization (PSO) and Grey Wolf Optimization (GWO).
• Developed a hybrid deep learning classifier integrating Convolutional Neural Networks (CNN) and Long Short-Term Memory (LSTM) networks.
• Evaluated the proposed IDS using the Industrial Control System (ICS) Cyber Attack Dataset (Power System Dataset) with simulated FDIA scenarios.

Main Results:

• The proposed IDS significantly outperformed traditional methods in detecting FDIAs.
• Hybrid feature selection reduced data dimensionality, improving computational efficiency and detection performance.
• The hybrid CNN-LSTM classifier achieved superior accuracy, recall, precision, and F-measure, ensuring reliable smart grid operation.

Conclusions:

• The dual-hybrid IDS framework offers a practical solution for detecting FDIAs in smart grids.
• The approach effectively enhances smart grid security by improving detection rates and reducing false positives.
• Future work should focus on real-world data validation, adaptive learning, and scalability for large-scale deployments.