Big Data Area: A Novel Network Performance Analysis Technique Based on Bayesian Traffic Classification Algorithm

Generally, the big data refers to one of the key topics because of the vast growth of the information and communication technology. The main contributor of networks performance is the traffic of the networks. Although the traffic data generated by individual users may not appear to be significant, the overall data generated across networks can produce a significant portion of the big data. Therefore, traffic related big data gathering in network area is, therefore, a challenging research area. One of the most effective solutions to address the big data challenge in ta network area is to utilize the advanced traffic modeling to facilitate the network performance analysis. Under this purpose, we describe the integrated KPI-MLDM-QoS technique that consists of Bayesian clustering method (KPI-MLDM) and Queue theory method (KPI-QoS), which aims at tackling this growing need by developing novel techniques capable to analyze big data set. A case study based on a real-world network traffic as well simulation to prove the integrated algorithm is implemented to test the efficiency and applicability of the proposed modeling and computing technique.