TY - GEN
T1 - Solar Panel Identification Under Limited Labels
AU - Luo, Shuman
AU - Weng, Yang
AU - Cook, Elizabeth
AU - Trask, Robert
AU - Blasch, Erik
N1 - Publisher Copyright:
© 2022 IEEE.
PY - 2022
Y1 - 2022
N2 - To better manage the unconventional two-way power flow, utilities are in urgent need to identify the locations of residential photovoltaic (PV) systems. With accurate PV location information, utilities can better maintain sustainable management and the safety of power grids. However, historical location records are unreliable and verification with human efforts is expensive, which challenges the PV location identification task. Thanks to the abundant information available from billing meter data, one can solve the problem via machine learning. As the labeled data can be very limited, supervised learning will be ineffective. Therefore, we propose new semi-supervised learning and one-class classification methods based on autoencoders. The proposed methods have been tested on a real-world utility data set and have shown superior detection accuracy in terms of accuracy and F1 score (= 0.95).
AB - To better manage the unconventional two-way power flow, utilities are in urgent need to identify the locations of residential photovoltaic (PV) systems. With accurate PV location information, utilities can better maintain sustainable management and the safety of power grids. However, historical location records are unreliable and verification with human efforts is expensive, which challenges the PV location identification task. Thanks to the abundant information available from billing meter data, one can solve the problem via machine learning. As the labeled data can be very limited, supervised learning will be ineffective. Therefore, we propose new semi-supervised learning and one-class classification methods based on autoencoders. The proposed methods have been tested on a real-world utility data set and have shown superior detection accuracy in terms of accuracy and F1 score (= 0.95).
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=85141520876&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85141520876&partnerID=8YFLogxK
U2 - 10.1109/PESGM48719.2022.9917215
DO - 10.1109/PESGM48719.2022.9917215
M3 - Conference contribution
AN - SCOPUS:85141520876
T3 - IEEE Power and Energy Society General Meeting
BT - 2022 IEEE Power and Energy Society General Meeting, PESGM 2022
PB - IEEE Computer Society
T2 - 2022 IEEE Power and Energy Society General Meeting, PESGM 2022
Y2 - 17 July 2022 through 21 July 2022
ER -