Cross-correlation based clustering and dimension reduction on multivariate time series for KPIs in a data processing system

In this paper, we investigate multi-dimensional time series data and we introduce a novel clustering approach based on the cross-correlation between the time series. The procedure is applied to Key Performance Indicators (KPIs) measured during a specific data processing system in order to identify connections between the various KPIs. The proposed technique allows for efficient visualization to reveal dependencies and connections between the attributes and also detects a small number of "relevant" attributes., i.e., select important features. Our method keeps background assumptions as minimal as possible. We also compare our findings to the results of other techniques of multivariate time series clustering.