Loced: Location-Aware Energy Disaggregation Framework

Providing detailed appliance level energy consumption information may lead consumers to understand their usage behavior and encourage them to optimize the energy usage. Non-intrusive load monitoring (NILM) or energy disaggregation aims to estimate appliance level energy consumption from the aggregate consumption data of households. NILM algorithms, proposed hitherto, are either centralized or do require high performance systems to derive appliance level data, owing to the computational complexity associated. This approach raises several issues related to scalability and privacy of consumer's data. In this paper, we present the Location-aware Energy Disaggregation Framework (LocED) that utilizes occupancy of users to derive accurate appliance level usage information. LocED framework limits the appliances considered for disaggregation based on the current location of occupants. Thus, LocED can provide realtime feedback on appliance level energy consumption and run on an embedded system locally at the household. We propose several accuracy metrics to study the performance of LocED. To test the robustness of LocED, we empirically evaluated it across multiple publicly available datasets. LocED has significantly high energy disaggregation accuracy while exponentially reducing the computational complexity. We also release our comprehensive dataset DRED (Dutch Residential Energy Dataset) for public use, which measures electricity, occupancy and ambient parameters of the household.