Power Disaggregation Considering Seasonality of Unmonitored Building Facilities

Estimating building energy efficiency and conservation effects remains challenging owing to a lack of detailed energy metering. To address unknown power consumption of facilities in commercial building energy management, disaggregation has been proposed to separate total power into multiple elements. However, assumptions are required when applying disaggregation to an actual building because not all facilities’ operating status can be monitored. Therefore, this study proposes that the power of the entire building can be accurately disaggregated by assuming that the power of unmonitored facilities is seasonal with daily periodicity. The proposed method is applied to a commercial building with 36 monitored outdoor air-conditioning units and unmonitored facilities, including indoor air-conditioning units, lighting, and other plug loads. Experimental results demonstrate that the proposed method can more precisely decompose the facility’s total power consumption than the conventional method. The proposed method is widely applicable to general commercial buildings and can contribute to energy-saving simulations and decision-making support for energy managers.