Metaheuristic-Driven Abnormal Traffic Detection Model for SDN Based on Improved Tyrannosaurus Optimization Algorithm

Nowadays, abnormal traffic detection for Software-Defined Networking (SDN) faces the challenges of large data volume and high dimensionality. Since traditional machine learning-based detection methods have the problem of data redundancy, the Metaheuristic Algorithm (MA) is introduced to select features before machine learning to reduce the dimensionality of data. Since a Tyrannosaurus Optimization Algorithm (TROA) has the advantages of few parameters, simple implementation, and fast convergence, and it shows better results in feature selection, TROA can be applied to abnormal traffic detection for SDN. However, TROA suffers from insufficient global search capability, is easily trapped in local optimums, and has poor search accuracy. Then, this paper tries to improve TROA, namely the Improved Tyrannosaurus Optimization Algorithm (ITROA). It proposes a metaheuristic-driven abnormal traffic detection model for SDN based on ITROA. Finally, the validity of the ITROA is verified by the benchmark function and the UCI dataset, and the feature selection optimization operation is performed on the InSDN dataset by ITROA and other MAs to obtain the optimized feature subset for SDN abnormal traffic detection. The experiment shows that the performance of the proposed ITROA outperforms compared MAs in terms of the metaheuristic-driven model for SDN, achieving an accuracy of 99.37% on binary classification and 96.73% on multiclassification.