DeepOPF-V: Solving AC-OPF Problems Efficiently

Wanjun HUANG; Xiang PAN; Minghua CHEN; Steven H. LOW

doi:10.1109/TPWRS.2021.3114092

DeepOPF-V: Solving AC-OPF Problems Efficiently

Wanjun HUANG
, Xiang PAN
, Minghua CHEN^*
, Steven H. LOW

^*Corresponding author for this work

Research output: Journal Publications › Journal Article (refereed) › peer-review

80 Citations (Scopus)

Abstract

AC optimal power flow (AC-OPF) problems need to be solved more frequently in the future to maintain stable and economic power system operation. To tackle this challenge, a deep neural network-based voltage-constrained approach (DeepOPF-V) is proposed to solve AC-OPF problems with high computational efficiency. Its unique design predicts voltages of all buses and then uses them to reconstruct the remaining variables without solving non-linear AC power flow equations. A fast post-processing process is also developed to enforce the box constraints. The effectiveness of DeepOPF-V is validated by simulations on IEEE 118/300-bus systems and a 2000-bus test system. Compared with existing studies, DeepOPF-V achieves decent computation speedup up to four orders of magnitude and comparable performance in optimality gap, while preserving feasibility of the solution.

Original language	English
Pages (from-to)	800-803
Number of pages	4
Journal	IEEE Transactions on Power Systems
Volume	37
Issue number	1
DOIs	https://doi.org/10.1109/TPWRS.2021.3114092
Publication status	Published - Jan 2022
Externally published	Yes

Bibliographical note

Publisher Copyright:
© 1969-2012 IEEE.

Funding

This work was supported in part by a Start-up Grant from the School of Data Science under Project 9380118, in part by the City University of Hong Kong, and in part by General Research Fund from Research Grants Council, Hong Kong, Project No. 11206821. Paper no. PESL-00064-2021.

Keywords

AC optimal power flow
deep neural network
voltage prediction

Access to Document

10.1109/TPWRS.2021.3114092

Cite this

@article{aa23fa7b78884b85b5e60e6d606c2b49,

title = "DeepOPF-V: Solving AC-OPF Problems Efficiently",

abstract = "AC optimal power flow (AC-OPF) problems need to be solved more frequently in the future to maintain stable and economic power system operation. To tackle this challenge, a deep neural network-based voltage-constrained approach (DeepOPF-V) is proposed to solve AC-OPF problems with high computational efficiency. Its unique design predicts voltages of all buses and then uses them to reconstruct the remaining variables without solving non-linear AC power flow equations. A fast post-processing process is also developed to enforce the box constraints. The effectiveness of DeepOPF-V is validated by simulations on IEEE 118/300-bus systems and a 2000-bus test system. Compared with existing studies, DeepOPF-V achieves decent computation speedup up to four orders of magnitude and comparable performance in optimality gap, while preserving feasibility of the solution.",

keywords = "AC optimal power flow, deep neural network, voltage prediction",

author = "Wanjun HUANG and Xiang PAN and Minghua CHEN and LOW, \{Steven H.\}",

note = "Publisher Copyright: {\textcopyright} 1969-2012 IEEE.",

year = "2022",

month = jan,

doi = "10.1109/TPWRS.2021.3114092",

language = "English",

volume = "37",

pages = "800--803",

journal = "IEEE Transactions on Power Systems",

issn = "0885-8950",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

number = "1",

}

TY - JOUR

T1 - DeepOPF-V: Solving AC-OPF Problems Efficiently

AU - HUANG, Wanjun

AU - PAN, Xiang

AU - CHEN, Minghua

AU - LOW, Steven H.

PY - 2022/1

Y1 - 2022/1

N2 - AC optimal power flow (AC-OPF) problems need to be solved more frequently in the future to maintain stable and economic power system operation. To tackle this challenge, a deep neural network-based voltage-constrained approach (DeepOPF-V) is proposed to solve AC-OPF problems with high computational efficiency. Its unique design predicts voltages of all buses and then uses them to reconstruct the remaining variables without solving non-linear AC power flow equations. A fast post-processing process is also developed to enforce the box constraints. The effectiveness of DeepOPF-V is validated by simulations on IEEE 118/300-bus systems and a 2000-bus test system. Compared with existing studies, DeepOPF-V achieves decent computation speedup up to four orders of magnitude and comparable performance in optimality gap, while preserving feasibility of the solution.

AB - AC optimal power flow (AC-OPF) problems need to be solved more frequently in the future to maintain stable and economic power system operation. To tackle this challenge, a deep neural network-based voltage-constrained approach (DeepOPF-V) is proposed to solve AC-OPF problems with high computational efficiency. Its unique design predicts voltages of all buses and then uses them to reconstruct the remaining variables without solving non-linear AC power flow equations. A fast post-processing process is also developed to enforce the box constraints. The effectiveness of DeepOPF-V is validated by simulations on IEEE 118/300-bus systems and a 2000-bus test system. Compared with existing studies, DeepOPF-V achieves decent computation speedup up to four orders of magnitude and comparable performance in optimality gap, while preserving feasibility of the solution.

KW - AC optimal power flow

KW - deep neural network

KW - voltage prediction

UR - https://www.scopus.com/pages/publications/85115678073

U2 - 10.1109/TPWRS.2021.3114092

DO - 10.1109/TPWRS.2021.3114092

M3 - Journal Article (refereed)

AN - SCOPUS:85115678073

SN - 0885-8950

VL - 37

SP - 800

EP - 803

JO - IEEE Transactions on Power Systems

JF - IEEE Transactions on Power Systems

IS - 1

ER -

DeepOPF-V: Solving AC-OPF Problems Efficiently

Abstract

Bibliographical note

Funding

Keywords

Access to Document

Other files and links

Fingerprint

Cite this