TY - GEN
T1 - GraphSAGE-Based Probabilistic Optimal Power Flow in Distribution System
AU - Ding, Yibo
AU - Wu, Huayi
AU - Xu, Zhao
AU - Yang, Hongming
N1 - Publisher Copyright:
© 2023 IEEE.
PY - 2023/12
Y1 - 2023/12
N2 - The large-scale penetration of wind and photovoltaic (PV) power generation brings significant uncertainties to the distribution system power flows. In this paper, a data-driven Graph Sample Aggregate (GraphSAGE) - based deep learning method is proposed to solve the probabilistic optimal power flow (POPF) problems for distribution systems, whose key concept is to flexibly aggregate and transform the nodal and branch features of the distribution system. By fully extracting the features via aggregation, the proposed method is capable of directly learning the implicit correlation among renewable and load uncertainties to improve the calculation accuracy as well as reducing the time and efforts on mathematical modelling. Cases studies on IEEE 33-node system are conducted to compare the effectiveness of the GraphSAGE-based method with other classical deep learning network based methods. Numerical simulation results further prove the effectiveness and accuracy of the GraphSAGE-based method on POPF problems.
AB - The large-scale penetration of wind and photovoltaic (PV) power generation brings significant uncertainties to the distribution system power flows. In this paper, a data-driven Graph Sample Aggregate (GraphSAGE) - based deep learning method is proposed to solve the probabilistic optimal power flow (POPF) problems for distribution systems, whose key concept is to flexibly aggregate and transform the nodal and branch features of the distribution system. By fully extracting the features via aggregation, the proposed method is capable of directly learning the implicit correlation among renewable and load uncertainties to improve the calculation accuracy as well as reducing the time and efforts on mathematical modelling. Cases studies on IEEE 33-node system are conducted to compare the effectiveness of the GraphSAGE-based method with other classical deep learning network based methods. Numerical simulation results further prove the effectiveness and accuracy of the GraphSAGE-based method on POPF problems.
KW - deep learning
KW - distribution system
KW - GraphSAGE network
KW - Probabilistic optimal power flow
UR - http://www.scopus.com/inward/record.url?scp=85180404369&partnerID=8YFLogxK
U2 - 10.1109/PowerCon58120.2023.10331518
DO - 10.1109/PowerCon58120.2023.10331518
M3 - Conference article published in proceeding or book
AN - SCOPUS:85180404369
T3 - Proceedings - 2023 International Conference on Power System Technology: Technological Advancements for the Construction of New Power System, PowerCon 2023
BT - Proceedings - 2023 International Conference on Power System Technology
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2023 International Conference on Power System Technology, PowerCon 2023
Y2 - 21 September 2023 through 22 September 2023
ER -
