On the effectiveness of isolation-based anomaly detection incloud data centers

摘要

The high volume of monitoring information generated by large-scale cloud infrastructures posesa challenge to the capacity of cloud providers in detecting anomalies in the infrastructure. Traditionalanomaly detection methods are resource-intensive and computationally complex fortraining and/or detection, what is undesirable in very dynamic and large-scale environment suchas clouds. Isolation-based methods have the advantage of low complexity for training and detectionand are optimized for detecting failures. In this work, we explore the feasibility of IsolationForest, an isolation-based anomaly detection method, to detect anomalies in large-scale clouddata centers.Wepropose amethodtocodetime-series information asextra attributes that enabletemporal anomaly detection and establish its feasibility to adapt to seasonality and trends in thetime-series and to be applied online and in real-time.