Investigating Robustness of Energy Management Maps for SMEs

Using the data from three small businesses, we are investigating robustness of the recently proposed Recurrence Quantitative Analysis (RQA) based method for energy management of small and medium enterprises. The method consists of two phases, the training phase where the map(s) of "usual" behaviour is obtained, and the operational phase where the new data is tested against the existing map(s). We measure how the output changes when there is a small change in input, with respect to the sampling rate, missing data and noise. Our results over three qualitatively different datasets show that the method is relatively robust and can be used for different SMEs.