Research and Application on Anomaly Detection of Dynamic Baseline Performance Time Series Data Based on Machine Learning

Anomaly detection of dynamic baseline performance time series data is an important problem in data center and cloud computing. In order to solve this problem, an anomaly detection method based on machine learning for the time series data of dynamic baseline performance was proposed. Firstly, sliding window is used to extract data features, and a variety of machine learning algorithms are used for anomaly detection. At the same time, a method based on dynamic baseline is proposed, which can adjust the baseline adaptively and detect anomalies. Experimental results show that the proposed method can achieve good anomaly detection results in data center and cloud computing.