Performance Evaluation of Clustering Algorithms for IP Traffic Recognition

Literature reports the huge work of IP traffic recognition using machine learning (ML) Algorithms. Data is divided into groups of similar objects or Clustering process groups the data instances that have similar characteristics without any previous supervision or guidance. Clustering analysis can be used for identification of IP traffic protocols effectively by measuring the external statistical attributes like packet length and inter arrival time. Our research work shows the analysis using K-means and DBSCAN clustering algorithm. Our approach is evaluated using accuracy and execution time for clustering model.