Network Traffic Analysis of Anomaly Detected Attacks Using Random Forest Algorithm in Cloud Environment

Abstract

This research aims to predict the total number of network connections or events that occur within a specific time period, number of different services or protocols used in the network connections, length of time for each network connection or event, frequency or rate of occurrence of a particular event or behavior within a given time period in a cloud environment. These are all the fundamental metrics used in network traffic analysis to quantify various aspects of network behavior and performance. By monitoring and analyzing these metrics, network administrators and security analysts can gain valuable insights into the nature of network traffic, detect anomalies or security threats, and optimize network performance and resource utilization. This research provides insights into effectively predicting network security logs using Random Forest with selected features from the real -time NSL Dataset.