NETWORK TRAFFIC CLASSIFICATION OF SOFTWARE DEFINED NETWORK USING DEEP LEARNING

Abstract

In order to cope with the monumental growth in network traffic, the field of networking is continuously progressing to accommodate this monumental growth in network traffic. As a matter of fact, a centralized control mechanism is provided by architectures such as Software Defined Networking (SDN) for the measurement, control, and prediction of network traffic, but the amount of information that the SDN controller receives is enormous. Recently, it has been suggested that machine learning (ML) is used to process that data. In fact, it is crucial to fine-grained network management, resource utilization, network security that, network traffic classification is used in a variety of network activities. To classify and analyze network traffic flows, the port-based approach, deep packet inspection, and ML are among the most widely used methods. Nevertheless, over the past several years, there has been an explosion in the number of users of the Internet, which has led to an explosive increase in Internet traffic. The exponential growth of Internet applications, which incur high computational costs, has made port-based, deep packet inspection (DPI), and ML approaches inefficient. It has been found that software-defined networking is redefining the network architecture by separating the control plane from the data plane and resulting in the creation of a centralized network controller that maintains a global view of the entire network. The aim of this paper is to propose a new deep learning model for software-defined networks able to accurately predict a wide range of traffic applications in a short time-frame to improve efficiency. In contrast to traditional ML approaches, theproposed model has been able to achieve better results in terms of accuracy, precision, recall, and F1-Score when compared with the traditional approaches. The performance metrics result from deep learning model indicates accuracy of 90.7%, F1-Score of 91%, Precision consistently of above 92%, Recall 88% and testing accuracy 92% respectively. It has been suggested that some further directions should be pursued to achieve future advances in this field based upon the results obtained.