An Empirical Study on Forecasting Using Decomposed Arrival Data of an Enterprise Computing System

This research utilizes several well known forecasting techniques in combination with Empirical Mode Decomposition (EMD) to investigate the trade-offs of EMD's decomposition (sifting) step for forecasting the arrival workload of an enterprise cluster. The research is based on earlier work on the forecasting potential of EMD. Results show that EMD helps to improve forecasting results. Parallelization is used to perform extensive investigation across the full range of data. Future research is to increase the statistical confidence in the level of improvements possible when EMD is used as a decomposition method for forecasting.