Anomaly Detection in NFV Using Tree-Based Unsupervised Learning Method

With the increased adoption of virtualized NFs in data center, it is crucial to address some of the challenges such as performance and availability of the applications in virtualized network environment. The normal operation of the network can be analyzed with respect to the usage of various resources like, CPU, memory, network and disk. Inefficient usage or over usage of these resources leads to anomalous behavior. Anomalies are often preceded by faults. It is important to detect anomalies before they occur. The detected anomalies can be used for corrective and optimization actions. This paper presents that; unsupervised machine learning algorithm performs better compared to supervised machine learning algorithms in detecting anomalies. Here we use isolation forest algorithm on time series dataset which is collected using monitoring agent collectd. Stress is induced to the computer using traffic monitoring generator and stress-ng. The results show that isolation forest algorithm gives better performance in anomaly detection with good anomaly score.