DeepOPF: Deep neural networks for optimal power flow

Xiang PAN

doi:10.1145/3486611.3492390

DeepOPF: Deep neural networks for optimal power flow

Xiang PAN^*

^*Corresponding author for this work

Research output: Book Chapters | Papers in Conference Proceedings › Conference (Extended Abstracts) › peer-review

18 Citations (Scopus)

Abstract

We develop a Deep Neural Network (DNN) approach, namely DeepOPF, for solving optimal power flow (OPF) problems that are critical for daily power system operation. DeepOPF leverages a DNN model to depict the high-dimensional load-to-solution mapping and can directly solve the OPF problem upon given load, excelling in fast computation process and desirable scalability. Simulation results for IEEE test cases show that DeepOPF generates feasible solutions with negligible (<0.2%) optimality loss and accelerates the computation time by up to two orders of magnitude as compared to a state-of-the-art solver.

Original language	English
Title of host publication	BuildSys '21: Proceedings of the 8th ACM International Conference on Systems for Energy-Efficient Buildings, Cities, and Transportation
Publisher	Association for Computing Machinery, Inc
Pages	250-251
Number of pages	2
ISBN (Electronic)	9781450391146
DOIs	https://doi.org/10.1145/3486611.3492390
Publication status	Published - 17 Nov 2021
Externally published	Yes
Event	The 8th ACM International Conference on Systems for Energy-Efficient Buildings, Cities, and Transportation, BuildSys '21 - Coimbra, Portugal Duration: 17 Nov 2021 → 18 Nov 2021

Conference

Conference	The 8th ACM International Conference on Systems for Energy-Efficient Buildings, Cities, and Transportation, BuildSys '21
Country/Territory	Portugal
City	Coimbra
Period	17/11/21 → 18/11/21

Bibliographical note

Publisher Copyright:
© 2021 Owner/Author.

Keywords

deep learning
deep neural network
optimal power flow

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1145/3486611.3492390

Cite this

@inbook{a2d3ab4800404b93a5556049fc933473,

title = "DeepOPF: Deep neural networks for optimal power flow",

abstract = "We develop a Deep Neural Network (DNN) approach, namely DeepOPF, for solving optimal power flow (OPF) problems that are critical for daily power system operation. DeepOPF leverages a DNN model to depict the high-dimensional load-to-solution mapping and can directly solve the OPF problem upon given load, excelling in fast computation process and desirable scalability. Simulation results for IEEE test cases show that DeepOPF generates feasible solutions with negligible (<0.2\%) optimality loss and accelerates the computation time by up to two orders of magnitude as compared to a state-of-the-art solver.",

keywords = "deep learning, deep neural network, optimal power flow",

author = "Xiang PAN",

note = "Publisher Copyright: {\textcopyright} 2021 Owner/Author.; The 8th ACM International Conference on Systems for Energy-Efficient Buildings, Cities, and Transportation, BuildSys '21 ; Conference date: 17-11-2021 Through 18-11-2021",

year = "2021",

month = nov,

day = "17",

doi = "10.1145/3486611.3492390",

language = "English",

pages = "250--251",

booktitle = "BuildSys '21: Proceedings of the 8th ACM International Conference on Systems for Energy-Efficient Buildings, Cities, and Transportation",

publisher = "Association for Computing Machinery, Inc",

address = "United States",

}

PAN, X 2021, DeepOPF: Deep neural networks for optimal power flow. in BuildSys '21: Proceedings of the 8th ACM International Conference on Systems for Energy-Efficient Buildings, Cities, and Transportation. Association for Computing Machinery, Inc, pp. 250-251, The 8th ACM International Conference on Systems for Energy-Efficient Buildings, Cities, and Transportation, BuildSys '21, Coimbra, Portugal, 17/11/21. https://doi.org/10.1145/3486611.3492390

DeepOPF: Deep neural networks for optimal power flow. / PAN, Xiang.
BuildSys '21: Proceedings of the 8th ACM International Conference on Systems for Energy-Efficient Buildings, Cities, and Transportation. Association for Computing Machinery, Inc, 2021. p. 250-251.

Research output: Book Chapters | Papers in Conference Proceedings › Conference (Extended Abstracts) › peer-review

TY - CHAP

T1 - DeepOPF: Deep neural networks for optimal power flow

AU - PAN, Xiang

PY - 2021/11/17

Y1 - 2021/11/17

N2 - We develop a Deep Neural Network (DNN) approach, namely DeepOPF, for solving optimal power flow (OPF) problems that are critical for daily power system operation. DeepOPF leverages a DNN model to depict the high-dimensional load-to-solution mapping and can directly solve the OPF problem upon given load, excelling in fast computation process and desirable scalability. Simulation results for IEEE test cases show that DeepOPF generates feasible solutions with negligible (<0.2%) optimality loss and accelerates the computation time by up to two orders of magnitude as compared to a state-of-the-art solver.

AB - We develop a Deep Neural Network (DNN) approach, namely DeepOPF, for solving optimal power flow (OPF) problems that are critical for daily power system operation. DeepOPF leverages a DNN model to depict the high-dimensional load-to-solution mapping and can directly solve the OPF problem upon given load, excelling in fast computation process and desirable scalability. Simulation results for IEEE test cases show that DeepOPF generates feasible solutions with negligible (<0.2%) optimality loss and accelerates the computation time by up to two orders of magnitude as compared to a state-of-the-art solver.

KW - deep learning

KW - deep neural network

KW - optimal power flow

UR - https://www.scopus.com/pages/publications/85120980001

U2 - 10.1145/3486611.3492390

DO - 10.1145/3486611.3492390

M3 - Conference (Extended Abstracts)

AN - SCOPUS:85120980001

SP - 250

EP - 251

BT - BuildSys '21: Proceedings of the 8th ACM International Conference on Systems for Energy-Efficient Buildings, Cities, and Transportation

PB - Association for Computing Machinery, Inc

T2 - The 8th ACM International Conference on Systems for Energy-Efficient Buildings, Cities, and Transportation, BuildSys '21

Y2 - 17 November 2021 through 18 November 2021

ER -

DeepOPF: Deep neural networks for optimal power flow

Abstract

Conference

Bibliographical note

Keywords

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this