Enhancing Model Learning: Quasi-Opposite Firefly Algorithm for Streamlined Feature Selection in DDoS Attack Detection

Abstract

Mobile edge computing (MEC) reduces latency for delay-sensitive applications by bringing computations closer to end users. However, this technology is vulnerable to security threats, notably Distributed Denial of Service (DDoS) attacks. DDoS attacks are characterised by distributed malicious nodes that flood the target with data packets, causing system unavailability or performance degradation. This contradicts the objective of the MEC, which is to reduce delay and latency. To address this, we propose a feature selection technique to improve the detection of DDoS attacks in MEC using machine learning techniques. The proposed approach employs quasi-opposite-based learning (QOBL), a concept often utilised in differential evolution algorithms, to modify the Firefly Algorithm (FA) to form a Quasi-Opposite Firefly Algorithm (QOFA) to optimise feature selection. FA excels at navigating complex feature spaces for global optimisation but suffers from premature convergence to local optima. QOBL mitigates this by guiding FA toward local solutions, improving efficiency and detection accuracy. By selecting only the most relevant features, the QOFA reduces computational complexity while maintaining robust performance. Simulations in MATLAB demonstrated that QOFA outperformed traditional FA, achieving a higher detection accuracy (up to 95%). This approach enhances the efficiency of machine learning models for DDoS detection in MEC, ensuring a reliable and low-latency network performance that is critical for real-time applications.