Engineering Technology & Applied Science Research, Год журнала: 2024, Номер 14(6), С. 19001 - 19008

Опубликована: Дек. 2, 2024

Most traditional IP networks face serious security and management challenges due to their rapid increase in complexity. SDN resolves these issues by the separation of control data planes, hence enabling programmability for centralized with flexibility. On other hand, its architecture makes very prone DDoS attacks, necessitating use advanced efficient IDSs. This study focuses on improving IDS performance environments through integration deep learning techniques novel feature selection methods. presents an Enhanced Maximum Relevance Minimum Redundancy (EMRMR) approach that incorporates a Mutual Information Feature Selection (MIFS) strategy new Contextual Coefficient Upweighting (CRCU) optimize early attack detection. Experiments inSDN dataset showed EMRMR achieved better precision, recall, F1-score, accuracy compared state-of-the-art approaches, especially when fewer features are selected. These results highlight efficiency proposed relevant minimal computational overhead, which enhances real-time capability environments.

Язык: Английский