Sustainable cyber-physical VANETs with AI-driven anomaly detection and energy-efficient multi-criteria routing using...

Area of Science:

• Computer Science
• Electrical Engineering
• Transportation Systems

Background:

• Vehicular Ad Hoc Networks (VANETs) are crucial for modern transportation, enabling vehicle-to-infrastructure communication.
• Existing anomaly detection methods in VANETs suffer from high false positives, poor adaptability, and significant computational load, hindering real-time performance and scalability.
• These limitations compromise the reliability and safety of intelligent transportation systems.

Purpose of the Study:

• To develop an effective Anomaly Detection using Machine Learning Algorithms (AD-MLA) framework for VANETs.
• To address the limitations of existing anomaly detection approaches, including false alarms, adaptability issues, and high computational demands.
• To enhance the security, efficiency, and scalability of real-time VANET environments for intelligent transportation.

Main Methods:

• The proposed AD-MLA framework utilizes a Random Forest model for accurate abnormal activity detection.
• It incorporates intelligent feature selection and data clustering techniques.
• An energy-efficient routing strategy is implemented, considering node energy, signal strength, hop count, and link stability.

Main Results:

• The AD-MLA framework demonstrated a significant reduction in false alarms and improved detection accuracy.
• It achieved high performance metrics: 95.33% accuracy, 96.09% recall, 94.25% computational efficiency, and 91.45% resource-use efficiency.
• The framework operates with lower energy and computational requirements compared to existing methods.

Conclusions:

• The AD-MLA framework provides a smart, rapid, and efficient security system suitable for real-time VANET environments.
• It effectively addresses scalability, latency, and energy challenges, making it ideal for high-reliability transportation systems.
• The integration of Random Forest, intelligent feature selection, and energy-efficient routing offers a robust solution for VANET security.