TY - GEN
T1 - Graph Mining for Classifying and Localizing Solar Panels in Distribution Grids
AU - Guo, Muhao
AU - Cui, Qiushi
AU - Weng, Yang
N1 - Funding Information:
ACKNOWLEDGMENT This work was supported by the National Key Research and Development Program (No. 2018YFB2100100)
Publisher Copyright:
© 2023 IEEE.
PY - 2023
Y1 - 2023
N2 - The growing photovoltaic (PV) penetration level in distribution networks has presented significant challenges to topology recovery of the distribution systems. Unfortunately, many utilities not only lack accurate topology information on the distribution grids but also have no record of photovoltaic panel locations. To acquire approximate locations of solar users, we propose a Graph Mining (GM) approach for solar panel localization. Due to the graphical structure of the grid and the temporal features of the power demand (Pd), we employ a solar panel classification algorithm that identifies graphical topology with time series data. Based on this time-series information, we design a graph construction algorithm and convert the time-series data to graph-type data. In the end, the graph-type data are fed into a graph neural network. By doing so, we transfer this problem into a graph classification problem and recognize the buses that are connected with solar panels. We validate the proposed method on several benchmark distribution grids and evaluate the model's capability under different system scenarios. The numerical results show that our algorithm can accurately detect solar panel locations in distribution feeders, thus improving the situational awareness of the secondary distribution grid.
AB - The growing photovoltaic (PV) penetration level in distribution networks has presented significant challenges to topology recovery of the distribution systems. Unfortunately, many utilities not only lack accurate topology information on the distribution grids but also have no record of photovoltaic panel locations. To acquire approximate locations of solar users, we propose a Graph Mining (GM) approach for solar panel localization. Due to the graphical structure of the grid and the temporal features of the power demand (Pd), we employ a solar panel classification algorithm that identifies graphical topology with time series data. Based on this time-series information, we design a graph construction algorithm and convert the time-series data to graph-type data. In the end, the graph-type data are fed into a graph neural network. By doing so, we transfer this problem into a graph classification problem and recognize the buses that are connected with solar panels. We validate the proposed method on several benchmark distribution grids and evaluate the model's capability under different system scenarios. The numerical results show that our algorithm can accurately detect solar panel locations in distribution feeders, thus improving the situational awareness of the secondary distribution grid.
KW - Distribution Grid
KW - Graph Neural Networks
KW - Solar Panel Location
KW - Topology Detection
UR - http://www.scopus.com/inward/record.url?scp=85163410747&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85163410747&partnerID=8YFLogxK
U2 - 10.1109/PandaFPE57779.2023.10140419
DO - 10.1109/PandaFPE57779.2023.10140419
M3 - Conference contribution
AN - SCOPUS:85163410747
T3 - Proceedings - 2023 Panda Forum on Power and Energy, PandaFPE 2023
SP - 1743
EP - 1747
BT - Proceedings - 2023 Panda Forum on Power and Energy, PandaFPE 2023
A2 - Liu, Junyong
A2 - Han, Xiaoyan
A2 - Hu, Weihao
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2023 Panda Forum on Power and Energy, PandaFPE 2023
Y2 - 27 April 2023 through 30 April 2023
ER -