The rational use and management of energy isconsidered a key societal and technological challenge. Homeenergy management systems (HEMS) have been introducedespecially in private home domains to support users in managingand controlling energy consuming devices. Recent studies haveshown that informing users about their habits with appliancesas well as their usage pattern can help to achieve energyreduction in private households. This requires instruments ableto monitor energy consumption at fine grain level and providethis information to consumers. While the most existing approachesfor load disaggregation and classification require high-frequencymonitoring data, in this paper we propose an approach thatexploits low-frequency monitoring data gathered by meters (i.e.,Smart Plugs) displaced in the home. Moreover, while the most existingworks dealing with appliance classification delegate the classificationtask to a remote central server, we propose a distributedapproach where data processing and appliance recognition areperformed locally in the Home Gateway. Our approach is basedon a distributed load monitoring system made of Smart Plugsattached to devices and connected to a Home Gateway via theZigBee protocol. The Home Gateway is based on the OSGiplatform, collects data from home devices, and hosts both dataprocessing and user interaction logic.
展开▼
