IEEE Transactions on Smart Grid · 2011 · 188 citations · 7 references
EngineeringElectrical EngineeringBuilding DiagnosticsEnergy SystemsTime Series AnalysisAnomaly DetectionBuilding AutomationBuilding Automation SystemsEnergy MeteringFault DetectionSystem IdentificationClusteringEnergy MonitoringIdentificationPower ConsumptionPower Consumption Modeling
The method presented in this paper is based on new residential appliances classification and an events detect model. The whole identification and monitoring system is designed in a financially viable and easily applicable method that is ensured by followed two aspects: first, the only senor is one a meter installed to the main electric supply of a residence; second, the model of appliance is absolutely unsupervised. The classification factors of the appliances are main power consumption unit and working styles. The new events detector is simple enough to install into the sensor/meter. The final identification uses mean-shift clustering and multidimensional linear discriminates. Actual trials in situ and their results are presented to reveal the performance of the system.
7
Nonintrusive appliance load monitoring
George Hart · Proceedings of the IEEE · 1992 · 3.1K citations
State of art on load monitoring methods
Hala Najmeddine, Khalil El Khamlichi Drissi, C. Pasquier et al. · 2008 · 81 citations
Architecture, Electrical Engineering, Demand Forecasting +16