Probabilistic Power Flow of Distribution System Based on a Graph-Aware Deep Learning Network

Huayi Wu; Minghao Wang; Zhao Xu; Youwei Jia

doi:10.1109/ICPSAsia52756.2021.9621647

Probabilistic Power Flow of Distribution System Based on a Graph-Aware Deep Learning Network

Huayi Wu, Minghao Wang, Zhao Xu, Youwei Jia

The Hong Kong Polytechnic University

Research output: Chapter in book / Conference proceeding › Conference article published in proceeding or book › Academic research › peer-review

5 Citations (Scopus)

Abstract

Quantifying the uncertainties in the distribution system is critical for economic load dispatch yet of great challenge. To address this issue, a graph-aware deep learning network (GADLN) for probabilistic power flow (PPF) calculation is proposed considering the unknown correlation distribution pattern among the wind and solar power generation. By fully utilizing the convolutional operation to aggregate the correlation among nodal active and reactive power injections, the distribution features of the distribution system state variables brought by uncertain wind, solar power, and load demand can be well captured. In this regard, the proposed GADLN can achieve enhanced effectiveness and efficiency without prior knowledge about the correlation of wind and solar power profiles. The case studies are carried out and compared with the state-of-art based on the IEEE 33-node system. Simulation results show that the proposed model outperforms the state-of-art in terms of PPF calculation efficiency and accuracy.

Original language	English
Title of host publication	2021 IEEE IAS Industrial and Commercial Power System Asia, I and CPS Asia 2021
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	105-109
Number of pages	5
ISBN (Electronic)	9781665434980
DOIs	https://doi.org/10.1109/ICPSAsia52756.2021.9621647
Publication status	Published - Jul 2021
Event	2021 IEEE IAS Industrial and Commercial Power System Asia, I and CPS Asia 2021 - Chengdu, China Duration: 18 Jul 2021 → 21 Jul 2021

Publication series

Name	2021 IEEE IAS Industrial and Commercial Power System Asia, I and CPS Asia 2021

Conference

Conference	2021 IEEE IAS Industrial and Commercial Power System Asia, I and CPS Asia 2021
Country/Territory	China
City	Chengdu
Period	18/07/21 → 21/07/21

Keywords

correlation
graph-aware
probabilistic power flow

ASJC Scopus subject areas

Energy Engineering and Power Technology
Electrical and Electronic Engineering
Industrial and Manufacturing Engineering
Mechanical Engineering

More information

10.1109/ICPSAsia52756.2021.9621647

Cite this

Wu, H., Wang, M., Xu, Z., & Jia, Y. (2021). Probabilistic Power Flow of Distribution System Based on a Graph-Aware Deep Learning Network. In 2021 IEEE IAS Industrial and Commercial Power System Asia, I and CPS Asia 2021 (pp. 105-109). (2021 IEEE IAS Industrial and Commercial Power System Asia, I and CPS Asia 2021). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICPSAsia52756.2021.9621647

Wu, Huayi ; Wang, Minghao ; Xu, Zhao et al. / Probabilistic Power Flow of Distribution System Based on a Graph-Aware Deep Learning Network. 2021 IEEE IAS Industrial and Commercial Power System Asia, I and CPS Asia 2021. Institute of Electrical and Electronics Engineers Inc., 2021. pp. 105-109 (2021 IEEE IAS Industrial and Commercial Power System Asia, I and CPS Asia 2021).

@inproceedings{507ab18bc9f34d8697979000e6ccc1e9,

title = "Probabilistic Power Flow of Distribution System Based on a Graph-Aware Deep Learning Network",

abstract = "Quantifying the uncertainties in the distribution system is critical for economic load dispatch yet of great challenge. To address this issue, a graph-aware deep learning network (GADLN) for probabilistic power flow (PPF) calculation is proposed considering the unknown correlation distribution pattern among the wind and solar power generation. By fully utilizing the convolutional operation to aggregate the correlation among nodal active and reactive power injections, the distribution features of the distribution system state variables brought by uncertain wind, solar power, and load demand can be well captured. In this regard, the proposed GADLN can achieve enhanced effectiveness and efficiency without prior knowledge about the correlation of wind and solar power profiles. The case studies are carried out and compared with the state-of-art based on the IEEE 33-node system. Simulation results show that the proposed model outperforms the state-of-art in terms of PPF calculation efficiency and accuracy.",

keywords = "correlation, graph-aware, probabilistic power flow",

author = "Huayi Wu and Minghao Wang and Zhao Xu and Youwei Jia",

note = "Funding Information: This work is supported in part by the National Natural Science Foundation of China Under Grant No. 62101473 and PolyU Start-up Fund for RAPs under the Strategic Hiring Scheme P0035553. Publisher Copyright: {\textcopyright} 2021 IEEE.; 2021 IEEE IAS Industrial and Commercial Power System Asia, I and CPS Asia 2021 ; Conference date: 18-07-2021 Through 21-07-2021",

year = "2021",

month = jul,

doi = "10.1109/ICPSAsia52756.2021.9621647",

language = "English",

series = "2021 IEEE IAS Industrial and Commercial Power System Asia, I and CPS Asia 2021",

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

pages = "105--109",

booktitle = "2021 IEEE IAS Industrial and Commercial Power System Asia, I and CPS Asia 2021",

}

Wu, H, Wang, M, Xu, Z & Jia, Y 2021, Probabilistic Power Flow of Distribution System Based on a Graph-Aware Deep Learning Network. in 2021 IEEE IAS Industrial and Commercial Power System Asia, I and CPS Asia 2021. 2021 IEEE IAS Industrial and Commercial Power System Asia, I and CPS Asia 2021, Institute of Electrical and Electronics Engineers Inc., pp. 105-109, 2021 IEEE IAS Industrial and Commercial Power System Asia, I and CPS Asia 2021, Chengdu, China, 18/07/21. https://doi.org/10.1109/ICPSAsia52756.2021.9621647

Probabilistic Power Flow of Distribution System Based on a Graph-Aware Deep Learning Network. / Wu, Huayi; Wang, Minghao; Xu, Zhao et al.
2021 IEEE IAS Industrial and Commercial Power System Asia, I and CPS Asia 2021. Institute of Electrical and Electronics Engineers Inc., 2021. p. 105-109 (2021 IEEE IAS Industrial and Commercial Power System Asia, I and CPS Asia 2021).

Research output: Chapter in book / Conference proceeding › Conference article published in proceeding or book › Academic research › peer-review

TY - GEN

T1 - Probabilistic Power Flow of Distribution System Based on a Graph-Aware Deep Learning Network

AU - Wu, Huayi

AU - Wang, Minghao

AU - Xu, Zhao

AU - Jia, Youwei

N1 - Funding Information: This work is supported in part by the National Natural Science Foundation of China Under Grant No. 62101473 and PolyU Start-up Fund for RAPs under the Strategic Hiring Scheme P0035553. Publisher Copyright: © 2021 IEEE.

PY - 2021/7

Y1 - 2021/7

N2 - Quantifying the uncertainties in the distribution system is critical for economic load dispatch yet of great challenge. To address this issue, a graph-aware deep learning network (GADLN) for probabilistic power flow (PPF) calculation is proposed considering the unknown correlation distribution pattern among the wind and solar power generation. By fully utilizing the convolutional operation to aggregate the correlation among nodal active and reactive power injections, the distribution features of the distribution system state variables brought by uncertain wind, solar power, and load demand can be well captured. In this regard, the proposed GADLN can achieve enhanced effectiveness and efficiency without prior knowledge about the correlation of wind and solar power profiles. The case studies are carried out and compared with the state-of-art based on the IEEE 33-node system. Simulation results show that the proposed model outperforms the state-of-art in terms of PPF calculation efficiency and accuracy.

AB - Quantifying the uncertainties in the distribution system is critical for economic load dispatch yet of great challenge. To address this issue, a graph-aware deep learning network (GADLN) for probabilistic power flow (PPF) calculation is proposed considering the unknown correlation distribution pattern among the wind and solar power generation. By fully utilizing the convolutional operation to aggregate the correlation among nodal active and reactive power injections, the distribution features of the distribution system state variables brought by uncertain wind, solar power, and load demand can be well captured. In this regard, the proposed GADLN can achieve enhanced effectiveness and efficiency without prior knowledge about the correlation of wind and solar power profiles. The case studies are carried out and compared with the state-of-art based on the IEEE 33-node system. Simulation results show that the proposed model outperforms the state-of-art in terms of PPF calculation efficiency and accuracy.

KW - correlation

KW - graph-aware

KW - probabilistic power flow

UR - http://www.scopus.com/inward/record.url?scp=85123364241&partnerID=8YFLogxK

U2 - 10.1109/ICPSAsia52756.2021.9621647

DO - 10.1109/ICPSAsia52756.2021.9621647

M3 - Conference article published in proceeding or book

AN - SCOPUS:85123364241

T3 - 2021 IEEE IAS Industrial and Commercial Power System Asia, I and CPS Asia 2021

SP - 105

EP - 109

BT - 2021 IEEE IAS Industrial and Commercial Power System Asia, I and CPS Asia 2021

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2021 IEEE IAS Industrial and Commercial Power System Asia, I and CPS Asia 2021

Y2 - 18 July 2021 through 21 July 2021

ER -

Wu H, Wang M, Xu Z, Jia Y. Probabilistic Power Flow of Distribution System Based on a Graph-Aware Deep Learning Network. In 2021 IEEE IAS Industrial and Commercial Power System Asia, I and CPS Asia 2021. Institute of Electrical and Electronics Engineers Inc. 2021. p. 105-109. (2021 IEEE IAS Industrial and Commercial Power System Asia, I and CPS Asia 2021). doi: 10.1109/ICPSAsia52756.2021.9621647

Probabilistic Power Flow of Distribution System Based on a Graph-Aware Deep Learning Network

Abstract

Publication series

Conference

Keywords

ASJC Scopus subject areas

More information

Other files and links

Fingerprint

Best Paper Award

Cite this

Probabilistic Power Flow of Distribution System Based on a Graph-Aware Deep Learning Network

Abstract

Publication series

Conference

Keywords

ASJC Scopus subject areas

More information

Other files and links

Fingerprint

Prizes

Best Paper Award

Cite this