A Temperature-Informed Data-Driven Approach for Behind-the-Meter Solar Disaggregation

Publication Date: 7/16/2023

Event: 2023 IEEE Power & Energy Society General Meeting (IEEE PES 2023)

Reference: pp. 1-5, 2023

Authors: Soroush Vahedi, University of Connecticut; Junbo Zhao, University of Connecticut; Yangmin Ding, NEC Laboratories America, Inc.; Elli Ntakou, Eversource Energy; Ting Wang, NEC Laboratories America, Inc.

Abstract: The lack of visibility to behind-the-meter (BTM) PVs causes many challenges to utilities. By constructing a dictionary of typical load patterns based on daily average temperatures and power consumptions, this paper proposes a temperature-informed data-driven approach for disaggregating BTM PV generation. This approach takes advantage of the high correlation between outside temperature and electricity consumption, as well as the high similarity between PV generation profiles. First, temperature-based fluctuation patterns are extracted from customer load demands without PV for each specific temperature range to build a temperature-based dictionary (TBD) in the offline stage. The dictionary is then used to disaggregate BTM PV in real-time. As a result, the proposed approach is more practical and provides a useful guideline in using temperature for operators in online mode. The proposed methodology has been verified using real smart meter data from London.

Publication Link: https://ieeexplore.ieee.org/document/10252739