Joint Energy Disaggregation of Behind-the-Meter PV and Battery Storage: A Contextually Supervised Source Separation Approach

Abstract

An increasing number of residential customers install the Hybrid Rooftop Solar Battery System (HRSBS). Most household HRSBS are installed behind the meter (BTM), where only netload is measured by the utility meter, which brings challenges to the system operation. Disaggregating BTM PV generation and battery charging/discharging profile of customers can enhance grid-edge observability. To this end, this paper proposes a joint energy disaggregation method to separate the PV generation and battery charging/discharging power from the netload. First, a Home Smart Battery Management model is built to generate the battery charging/discharging profile. Second, an optimal disaggregation model is established based on Contextually Supervised Source Separation method. Third, the feature vectors of PV, load, and battery are extracted as the input of the disaggregation model. Case study results show that the proposed method has promising disaggregation performance for PV and original load, and the estimation error of battery charging/discharging profile is less than 30% in most cases. Finally, the impact of PV system size and battery capacity on the performance of the proposed method is analyzed.