Machine Learning-Based Attack Detection and Mitigation with Multi-Controller Placement Optimization over SDN Environment

The increasing complexity and scale of modern software-defined networking demands advanced solutions to address security challenges, particularly distributed denial-of-service (DDoS) attacks in multi-controller environments. Traditional single-controller implementations are struggling to effectively counter sophisticated cyber threats, necessitating a faster and scalable solution. This study introduces a novel approach for attack detection and mitigation with optimized multi-controller software-defined networking (SDN) using machine learning (ML). The study focuses on the design, implementation, and assessment of the optimal placement of multi-controllers using K-means++ and OPTICS in real topologies and an intrusion detection system (IDS) using the XGBoost classification algorithm to detect and mitigate attacks efficiently with accuracy, precision, and recall of 98.5%, 97.0%, and 97.0%, respectively. Additionally, the IDS decouples from the controllers, preserves controller resources, and allows for efficient near-real-time attack detection and mitigation. The proposed solution outperforms well by autonomously identifying anomalous behaviors in networks through successfully combining the controller placement problem (CPP) and DDoS security.