Nowadays computer networks have to fulfil several essential requirements like ease of use, efficiency, security, easy manageability, as well as easy configurability. The concept of Software Defined Networking (SDN) has been developed especially for these purposes. It represents a new technology whose penetration is continuously growing. The novel idea in SDN is that it removes the control plane from network hardware and implements it in software. This solution creates the possibility of a dynamic programmatic access and a more flexible network administration. This paper gives an overview of the structure and key features of SDN as well as presents some advantages of its application ÖsszefoglalásAz informatikai hálózatok megvalósítása során nagy hangsúlyt kell fektetni a könnyű kezelhetőségre, hatékonyságra, és a biztonságára. Fontos szempont még a könnyű felügyelhetőség és konfigurálhatóság. A Software Defined Networking (SDN) vagy szoftver által definiált hálózat paradigma pontosan ezt a lehetőséget nyújtja. Ez egy napjainkban egyre jobban elterjedt technológia, ami biztosítja azt, hogy az adatsík (fizikai eszközök egyszerű adattovábbítási feladat ellátása) és a vezérlő sík (irányítás felsőbb rétegből) külön váljon, és ezáltal könnyebb legyen a hálózat megvalósítása, mind költséghatékonyság, mind optimalizálás szempontjából.

Feature selection is a crucial step in machine learning, aiming to identify the most relevant features in high-dimensional data, in order to reduce the computational complexity of model development and improve its generalization performance. Ensemble feature ranking methods combine the results of several feature selection techniques to identify a subset of the most relevant features for a given task. In many cases, they produce a more comprehensive ranking of features than the individual methods used in them. This paper presents a novel approach to ensemble feature ranking, which uses a weighted average of the individual ranking scores calculated by the individual methods. The optimal weights are determined using a Taguchi-type design of experiments. The proposed methodology significantly improves classification performance on the CSE-CIC-IDS2018 dataset, particularly for attack types where traditional average-based feature ranking score combinations resulted in low classification metrics.

Feature selection is a crucial step in machine learning, aiming to identify the most relevant features in high-dimensional data in order to reduce the computational complexity of model development and improve generalization performance. Ensemble feature-ranking methods combine the results of several feature-selection techniques to identify a subset of the most relevant features for a given task. In many cases, they produce a more comprehensive ranking of features than the individual methods used alone. This paper presents a novel approach to ensemble feature ranking, which uses a weighted average of the individual ranking scores calculated using these individual methods. The optimal weights are determined using a Taguchi-type design of experiments. The proposed methodology significantly improves classification performance on the CSE-CIC-IDS2018 dataset, particularly for attack types where traditional average-based feature-ranking score combinations result in low classification metrics.