Developing Machine Learning Based Framework for Network Traffic Prediction

Abstract

Network traffic analysis is a crucial step in developing efficient congestion control systems and identifying valid and malicious packets. Because network resources are apportioned based on predicted usage, these solutions reduce network congestion. For a variety of reasons, including dynamic bandwidth allocation, network security, and network planning, the ability to forecast network traffic is critical. Machine learning (ML) techniques to network traffic analysis have received a lot of interest. This article outlines an approach for analyzing network traffic. Three machine learning-based methodologies make up the methodology. The experimental investigation employed the NSL KDD data set. On the basis of accuracy and other criteria, KNN, Support vector machine, and nave bayes are compared.