The rational use and management of energy is a key objective for the evolution towards the smart grid. In particular in the private home domain the adoption of wide-scale energy consumption monitoring techniques can help end users in optimizing energy consumption behaviors. While most existing approaches for load disaggregation and classification requires high-frequency monitoring data, in this paper we propose an approach for detecting and identifying the appliances in use by analysing low-frequency monitoring data gathered by meters (i.e. smart plugs) distributed in the home. Our approach implements a supervised classification algorithm with artificial neural networks and has been tested with a dataset of power traces collected in real-world home settings.
ANN-based Appliance Recognition from Low-frequency Energy Monitoring Data
F. Paganelli;D. Giuli;
2013-01-01
Abstract
The rational use and management of energy is a key objective for the evolution towards the smart grid. In particular in the private home domain the adoption of wide-scale energy consumption monitoring techniques can help end users in optimizing energy consumption behaviors. While most existing approaches for load disaggregation and classification requires high-frequency monitoring data, in this paper we propose an approach for detecting and identifying the appliances in use by analysing low-frequency monitoring data gathered by meters (i.e. smart plugs) distributed in the home. Our approach implements a supervised classification algorithm with artificial neural networks and has been tested with a dataset of power traces collected in real-world home settings.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
