User-Centered Nonintrusive Electricity Load Monitoring for Residential Buildings

摘要: This paper presents a nonintrusive electricity load-monitoring approach that provides feedback on the energy consumption and operational schedule of electrical appliances in residential building. utilizes simple algorithms for detecting classifying events basis voltage current measurements obtained at main circuit panel home. To address necessary training calibration, this is designed around end-user relies user input to continuously improve its performance. The interaction processes are described detail. Three data sets were collected with prototype system (from power strip laboratory, house, an apartment unit) test performance algorithms. event detector achieved true positive false rates 94 0.26%, respectively. When combined classification task, overall accuracy (correctly detected classified events) was 82%. advantages a...