Data mining as an enabling technology for Home Energy Management System

We have designed Home Energy Management System which is able not only to collect and display data, switch off (on) the appliances, but also to deal with identification of the appliance(s) plugged-in to a single power socket sensor. For that purpose, in this paper we are proposing a data mining algorithm that analyzes the collected consumption data from different appliances in order to identify a cluster of each of the appliances, or a cluster of a group of appliances plugged-in in the same time to a single power socket sensor. We have achieved high clustering accuracy for the monitored values for the power consumption of appliances. Hence, the presented data mining algorithm enables successful identification of the operating states of the appliances plugged-in to a multi-socket extension. Additionally, we discuss the unforeseen challenging issues that appeared during the evaluation phase of the algorithm, in order to provide efficient identification of a household appliance (or group of appliances) eligible for further remote control.