Detection of Anomalies in Household Appliances from Disaggregated Load Consumption

The detection of anomalous power consumption in household appliances plays a key role for the optimization of grid operations and for reducing unwanted electrical absorptions in residential buildings. Smart Plugs, Smart Appliances and other appliance-level monitoring devices allow to continuously monitor the power consumption of individual appliances present in the house. This work is aimed at detecting electrical anomalies in household appliances by analyzing the disaggregated load consumption derived from appliance-level monitoring devices. For this purpose, we implemented an anomaly detection framework which monitors the hourly energy consumption of three common sources of power absorption: the baseline, the fridge and the electrical devices. Here, we focused our analysis on two kinds of anomalies: single-point deviations and anomalous trends. The analysis of single-point deviations allowed us to identify short-term power peaks due either to unexpected electrical faults or sudden variations in end-users routines. The analysis of anomalous trends revealed several cases in which the end-users gradually increased their ordinary power consumption profile towards more energy-intensive practices. In summary, the results of our work showed that the power consumption derived from appliance-level load monitoring can be used to detect several anomalous power consumption in household appliances.