TY - GEN
T1 - An Analysis of the Reliability of AC Optimal Power Flow Deep Learning Proxies
AU - Dinh, My H.
AU - Fioretto, Ferdinando
AU - Mohammadian, Mostafa
AU - Baker, Kyri
N1 - Publisher Copyright:
© 2023 IEEE.
PY - 2023
Y1 - 2023
N2 - Optimal Power Flow (OPF) is a challenging problem in power systems, and recent research has explored the use of Deep Neural Networks (DNNs) to approximate OPF solutions with reduced computational times. While these approaches show promising accuracy and efficiency, there is a lack of analysis of their robustness. This paper addresses this gap by investigating the factors that lead to both successful and suboptimal predictions in DNN-based OPF solvers. It identifies power system features and DNN characteristics that contribute to higher prediction errors and offers insights on mitigating these challenges when designing deep learning models for OPF.
AB - Optimal Power Flow (OPF) is a challenging problem in power systems, and recent research has explored the use of Deep Neural Networks (DNNs) to approximate OPF solutions with reduced computational times. While these approaches show promising accuracy and efficiency, there is a lack of analysis of their robustness. This paper addresses this gap by investigating the factors that lead to both successful and suboptimal predictions in DNN-based OPF solvers. It identifies power system features and DNN characteristics that contribute to higher prediction errors and offers insights on mitigating these challenges when designing deep learning models for OPF.
UR - http://www.scopus.com/inward/record.url?scp=85180014618&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85180014618&partnerID=8YFLogxK
U2 - 10.1109/ISGT-LA56058.2023.10328223
DO - 10.1109/ISGT-LA56058.2023.10328223
M3 - Conference contribution
AN - SCOPUS:85180014618
T3 - 2023 IEEE PES Innovative Smart Grid Technologies Latin America, ISGT-LA 2023
SP - 170
EP - 174
BT - 2023 IEEE PES Innovative Smart Grid Technologies Latin America, ISGT-LA 2023
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2023 IEEE PES Innovative Smart Grid Technologies Latin America, ISGT-LA 2023
Y2 - 6 November 2023 through 9 November 2023
ER -