Smart architecture for software-defined networking

Software-defined networks (SDN) seek to solve the problems in current network schemes by simplifying their management through reprogrammability and accessibility overall infrastructure. One aspect improve SDN-based is precise classification of your traffic load, this can various aspects such as quality service, dynamic access control, prioritized random access, among others. This research aims propose a conceptual architecture SDN evaluate different machine learning methods for classification. To end, architectures are analyzed modules proposed strengthen with help low computational cost classifiers. The proposes following main modules: Capture traces module, Learning Engine ML-model Flow classifier. determine model be used classifier modules, classifiers were evaluated using database traffic, result, it was determined that gradient boosting algorithm most suitable integrated architecture.