TY - JOUR
T1 - Solar Panel Identification Via Deep Semi-Supervised Learning and Deep One-Class Classification
AU - Cook, Elizabeth
AU - Luo, Shuman
AU - Weng, Yang
N1 - Funding Information:
This work was supported in part by NSF under Grants 1810537
Publisher Copyright:
© 1969-2012 IEEE.
PY - 2022/7/1
Y1 - 2022/7/1
N2 - As residential photovoltaic (PV) system installations continue to increase rapidly, utilities need to identify the locations of these new components to manage the unconventional two-way power flow and maintain sustainable management of distribution grids. But, historical records are unreliable and constant re-assessment of active residential PV locations is resource-intensive. To resolve these issues, we propose to model the solar detection problem in a machine learning setup based on labeled data, e.g., supervised learning. However, the challenge for most utilities is limited labels or labels on only one type of users. Therefore, we design new semi-supervised learning and one-class classification methods based on autoencoders, which greatly improve the nonlinear data representation of human behavior and solar behavior. The proposed methods have been tested and validated not only on synthetic data based on a publicly available data set but also on real-world data from utility partners. The numerical results show robust detection accuracy, laying down the foundation for managing distributed energy resources in distribution grids.
AB - As residential photovoltaic (PV) system installations continue to increase rapidly, utilities need to identify the locations of these new components to manage the unconventional two-way power flow and maintain sustainable management of distribution grids. But, historical records are unreliable and constant re-assessment of active residential PV locations is resource-intensive. To resolve these issues, we propose to model the solar detection problem in a machine learning setup based on labeled data, e.g., supervised learning. However, the challenge for most utilities is limited labels or labels on only one type of users. Therefore, we design new semi-supervised learning and one-class classification methods based on autoencoders, which greatly improve the nonlinear data representation of human behavior and solar behavior. The proposed methods have been tested and validated not only on synthetic data based on a publicly available data set but also on real-world data from utility partners. The numerical results show robust detection accuracy, laying down the foundation for managing distributed energy resources in distribution grids.
KW - Autoencoder
KW - Detection
KW - Locations
KW - One-class classification
KW - Semi-supervised learning
KW - Solar panels
UR - http://www.scopus.com/inward/record.url?scp=85133191006&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85133191006&partnerID=8YFLogxK
U2 - 10.1109/TPWRS.2021.3125613
DO - 10.1109/TPWRS.2021.3125613
M3 - Article
AN - SCOPUS:85133191006
SN - 0885-8950
VL - 37
SP - 2516
EP - 2526
JO - IEEE Transactions on Power Systems
JF - IEEE Transactions on Power Systems
IS - 4
ER -