Analysis on the Utilization of Machine Learning in the Implementation and Designing of an Intelligent Ddos Attack Detection Model for Sdn

A novel method for creating dynamic, flexible, affordable, and manageable computer network architecture is called Software-Defined Networking, or SDN. In order to promote design suitable with the present networks that use infrastructure-hosted services computing, the SDN paradigm delivers virtualized network services. By sorting out the control plane from the network plane, Software-Defined Networks (SDN) offer a promising alternative to traditional networks. Attacks recognized as denial of service (DoS) occur when a high number of packets from compromised machines flood the network. Distributed Denial of Service (DDoS) assaults are one type of these attacks in which multiple infected machines aim at a target at the same time. The Intelligent DDoS Attack Detection Model Designing for SDN Using Machine Learning is presented in this research. A denial-of-service (DDoS) assault is when several coordinated systems attack a certain server simultaneously. This study uses the Random Forest (RF) classifier as a machine learning model. Python was utilized as a simulator in the suggested work, and the UNWS-np-15 dataset was taken from the GitHub source. Exactness, correctness, Recall, and F1-Score characteristics are used to compare Random Forest's performance with other classifiers. The findings of our experiments demonstrate that Random Forest (RF) is more efficient than other models when compared to previous research works.