TY - JOUR
T1 - Physical-Model-Aided Data-Driven Linear Power Flow Model
T2 - An Approach to Address Missing Training Data
AU - Shao, Zhentong
AU - Zhai, Qiaozhu
AU - Guan, Xiaohong
N1 - Publisher Copyright:
© 1969-2012 IEEE.
PY - 2023/5/1
Y1 - 2023/5/1
N2 - Data-driven linear power flow (D-LPF) models are prevalent due to their excellent accuracy. Typically, D-LPF models rely on sufficient training data. However, in practice, the training data may be insufficient due to recording errors or limited measurement conditions. To address this practical and important issue, this letter presents a physical-model-aided data-driven linear power flow (PD-LPF) model, in which, physical model parameters are introduced to assist the data-driven training process, thereby avoiding unreasonable training results, and guaranteeing linearization accuracy for critical operating points with the maximum probability. The proposed method is applicable for both transmission and distribution systems. Compared to current LPF models, the PD-LPF model exhibits excellent accuracy and robustness under severe missing-data conditions.
AB - Data-driven linear power flow (D-LPF) models are prevalent due to their excellent accuracy. Typically, D-LPF models rely on sufficient training data. However, in practice, the training data may be insufficient due to recording errors or limited measurement conditions. To address this practical and important issue, this letter presents a physical-model-aided data-driven linear power flow (PD-LPF) model, in which, physical model parameters are introduced to assist the data-driven training process, thereby avoiding unreasonable training results, and guaranteeing linearization accuracy for critical operating points with the maximum probability. The proposed method is applicable for both transmission and distribution systems. Compared to current LPF models, the PD-LPF model exhibits excellent accuracy and robustness under severe missing-data conditions.
KW - Data-driven
KW - chance constraints
KW - distributionally robust
KW - linear power flow
KW - missing data
UR - http://www.scopus.com/inward/record.url?scp=85151392334&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85151392334&partnerID=8YFLogxK
U2 - 10.1109/TPWRS.2023.3256120
DO - 10.1109/TPWRS.2023.3256120
M3 - Article
AN - SCOPUS:85151392334
SN - 0885-8950
VL - 38
SP - 2970
EP - 2973
JO - IEEE Transactions on Power Systems
JF - IEEE Transactions on Power Systems
IS - 3
ER -