Detecting Anomaly Teletraffic Using Stochastic Self-Similarity Based on Hadoop

In recent years, the quantity of teletraffic is rapidly growing because of the explosive increase of Internet users and its applications. The needs of collection, storage, management, analysis, and measurement of the subsequent teletraffic have been emerged as one of very important issues. So far many studies for detecting anomaly teletraffic have been done. However, measurement and analysis studies for big data in cloud computing environments are not actively being made based on Hadoop. Thus, this paper presents for detecting anomaly teletraffic using stochastic self-similarity based on Hadoop. All simulations are conducted under control of our proposed platform, called ATM tool, for anomaly teletraffic intrusion detection system on Hadoop. Our numerical results show that the values of the estimated Hurst parameter obtained from the anomaly teletraffic are much higher when compared to ordinary local area network traffic.