A compumetrical approach for analysis and clustering of computer system performance variables

Various statistical models have been constructed for analyzing the workload variables of a computer system, but most of these models fail to analyze each variable separately and identify job groups by hardware consumption patterns. In this paper we propose a compumetrical approach to analyze the computer system performance variables and to cluster the jobs into homogeneous groups. It involves using univariable and multivariable analysis and graphical methods for analyzing the variables. This approach enables us to explore data thoroughly, to look for patterns and clusters, to confirm or disprove the expected hardware consumption, and to discover new phenomena.