Automated modeling of real real-time anomaly detection using non -parametric statistical technique for data streams in cloud environments

Abstract

Online anomaly detection plays a vital role in improving the performance of cloud data centers by identifying unusual behaviors. In this paper, we propose an online anomaly detection framework using non-parametric statistical technique in cloud data center. The major advantage of the proposed work is its capability of automatic re-computing of the model, according to the fundamental changes in the data. In order to determine the accuracy of the proposed work, we experiment it to data collected from RUBis cloud testbed (Dataset 1) and Yahoo Cloud Serving Benchmark (YCSB) (Dataset 2). Our experimental results show the greater accuracy in terms of True Positive Rate (TPR), False Positive Rate (FPR), True Negative Rate (TNR) and False Negative Rate (FNR).