Scholarlink

In the rapidly evolving landscape of Software Defined Networks (SDNs), network security is of paramount importance. This research paper presents a comprehensive study on anomaly detection and traffic analysis in SDNs using machine learning algorithms. The study addresses a critical research gap by proposing an effective methodology for detecting network anomalies and analyzing traffic patterns. Leveraging a carefully selected dataset, we evaluate the performance of Logistic Regression, Decision Tree, Random Forest, Neural Networks and Hybrid Models. The results demonstrate the superior performance of the hybrid model built using Decision Tree and Neural Networks and the competitive accuracy of Neural Networks in SDN anomaly detection.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Predicting and Evaluating Anomaly Detection and Traffic Analysis on Software Defined Networks Using a Hybrid Machine Learning Approach

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • S. Darshan,
  • N. Radhika,
  • G. Radhika

摘要

In the rapidly evolving landscape of Software Defined Networks (SDNs), network security is of paramount importance. This research paper presents a comprehensive study on anomaly detection and traffic analysis in SDNs using machine learning algorithms. The study addresses a critical research gap by proposing an effective methodology for detecting network anomalies and analyzing traffic patterns. Leveraging a carefully selected dataset, we evaluate the performance of Logistic Regression, Decision Tree, Random Forest, Neural Networks and Hybrid Models. The results demonstrate the superior performance of the hybrid model built using Decision Tree and Neural Networks and the competitive accuracy of Neural Networks in SDN anomaly detection.