A Comparative Study for SDN Security Based on Machine Learning

In the past decade, traditional networks have been utilized to transfer data between more than one node. The primary problem related formal is their stable essence, which makes them incapable of meeting requirements nodes recently inserted into network. Thus, are substituted by a Software Defined Network (SDN). latter can be construct structure for intensive applications like big data. this paper, comparative investigation Deep Neural (DNN) and Machine Learning (ML) techniques that uses various feature selection undertaken. ML employed in approach decision tree (DT), Naïve Bayes (NB), Support Vector (SVM). proposed tested experimentally evaluated using an available NSL–KDD dataset. This dataset includes 41 features 148,517 samples. To evaluate techniques, several estimation measurements calculated. results prove DT most accurate effective approach. Furthermore, evaluation indicate efficacy presented compared earlier studies.