Sing Network Slicing And NFV Technology
Zahra Mohammady, Reza Azmi · 2020
With the growth of the network and the emergence of 5G networks, it is not possible to achieve a reliable service with proper performance in all cases of use with a single design. Recent advances in virtualization and machine learning techniques have ushered in a new era of network management. By separating network functions from traditional hardware, Network Function virtualization (NFV) is expected to provide more flexible management of network functions and efficient sharing of network resources. Network slicing with Software-Defined Networks (SDN) and NFV creates the flexible deployment of network functions belonging to several Service Function Chains (SFC) on a common infrastructure. In this paper, with the help of NFV capabilities as well as existing machine learning methods, a framework for intelligent network slicing is proposed. In this method, Convolutional Neural Networks (CNN) are used to analyze network traffic and classify them. This method can classify traffic without human intervention for feature extraction. By using CNN results, we were able to make the network slice with 97% accuracy.