Autonomous Load Disaggregation Approach based on Active Power Measure...

With the help of smart metering valuable information of the appliance usage can be retrieved. In detail, non-intrusive load monitoring (NILM), also called load disaggregation, tries to identify appliances in the power draw of anhousehold. In this paper an unsupervised load disaggregation approach is proposed that works without a priori knowledge aboutappliances. The proposed algorithm works autonomously in realtime. The number of used appliances and the correspondingappliance models are learned in operation and are progressivelyupdated. The proposed algorithm is considering each useful andsuitable detected power state. The algorithm tries to detect powerstates corresponding to on/off appliances as well as to multi-stateappliances based on active power measurements in 1s resolution.We evaluated the novel introduced load disaggregation approachon real world data by testing the possibility to disaggregateenergy demand on appliance level.