Detecting correlation between server resources for system management
作者：
Highlights：
• Evidence of correlation between resource measures facilitates system management.
• Capacity planning, forecasting, anomaly detection benefit of this evidence.
• Existing models fail in finding correlation when resource data variability is too high.
• We propose a model that captures correlation independently of datasets variability.
• The proposed model improves accuracy and robustness of existing algorithms.
摘要
•Evidence of correlation between resource measures facilitates system management.•Capacity planning, forecasting, anomaly detection benefit of this evidence.•Existing models fail in finding correlation when resource data variability is too high.•We propose a model that captures correlation independently of datasets variability.•The proposed model improves accuracy and robustness of existing algorithms.
论文关键词：Correlation model,Data analysis,High variability
论文评审过程：Received 23 July 2012, Revised 9 October 2013, Accepted 7 January 2014, Available online 10 January 2014.
论文官网地址：https://doi.org/10.1016/j.jcss.2014.01.002
