Convolutional Deep Leaning-Based Distribution System Topology Identification with Renewables

Huayi Wu; Zhao Xu; Minghao Wang

doi:10.1109/CIYCEE53554.2021.9676913

Convolutional Deep Leaning-Based Distribution System Topology Identification with Renewables

Huayi Wu
, Zhao Xu
, Minghao Wang

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

Obtaining the distribution system topology states timely is critical for system monitoring while challenged by correlations brought by high penetrated renewable energy sources (RES). To address this issue, a deep learning model is proposed for distribution system topology identification considering the underlying complex correlations of renewables. Specifically, to remove the dependence of the power system model parameters like line impedance, the input of the model only consists of the voltage magnitudes. Then, this is fed into the proposed Convolutional deep learning model (CDLM), which can fully capture the data features and thus classify the topology of the grid to hedge against the correlations of the RES and thus enhance the identification accuracy. The simulation results demonstrate the accuracy and efficiency of the proposed model in the IEEE 33-node distribution system.

Original language	English
Title of host publication	2021 IEEE 2nd China International Youth Conference on Electrical Engineering, CIYCEE 2021
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	9781665400640
DOIs	https://doi.org/10.1109/CIYCEE53554.2021.9676913
Publication status	Published - Dec 2021
Event	2nd IEEE China International Youth Conference on Electrical Engineering, CIYCEE 2021 - Chengdu, China Duration: 15 Dec 2021 → 17 Dec 2021

Publication series

Name	2021 IEEE 2nd China International Youth Conference on Electrical Engineering, CIYCEE 2021

Conference

Conference	2nd IEEE China International Youth Conference on Electrical Engineering, CIYCEE 2021
Country/Territory	China
City	Chengdu
Period	15/12/21 → 17/12/21

UN SDGs

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

SDG 7 Affordable and Clean Energy

Keywords

correlation
deep learning
Distribution system topology identification
renewable energy

ASJC Scopus subject areas

Energy Engineering and Power Technology
Electrical and Electronic Engineering
Mechanical Engineering
Safety, Risk, Reliability and Quality
Control and Optimization

More information

10.1109/CIYCEE53554.2021.9676913

Cite this

Wu, H., Xu, Z., & Wang, M. (2021). Convolutional Deep Leaning-Based Distribution System Topology Identification with Renewables. In 2021 IEEE 2nd China International Youth Conference on Electrical Engineering, CIYCEE 2021 (2021 IEEE 2nd China International Youth Conference on Electrical Engineering, CIYCEE 2021). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/CIYCEE53554.2021.9676913

Wu, Huayi ; Xu, Zhao ; Wang, Minghao. / Convolutional Deep Leaning-Based Distribution System Topology Identification with Renewables. 2021 IEEE 2nd China International Youth Conference on Electrical Engineering, CIYCEE 2021. Institute of Electrical and Electronics Engineers Inc., 2021. (2021 IEEE 2nd China International Youth Conference on Electrical Engineering, CIYCEE 2021).

@inproceedings{fa9cb04a894749c7ad1a31747846ec6f,

title = "Convolutional Deep Leaning-Based Distribution System Topology Identification with Renewables",

abstract = "Obtaining the distribution system topology states timely is critical for system monitoring while challenged by correlations brought by high penetrated renewable energy sources (RES). To address this issue, a deep learning model is proposed for distribution system topology identification considering the underlying complex correlations of renewables. Specifically, to remove the dependence of the power system model parameters like line impedance, the input of the model only consists of the voltage magnitudes. Then, this is fed into the proposed Convolutional deep learning model (CDLM), which can fully capture the data features and thus classify the topology of the grid to hedge against the correlations of the RES and thus enhance the identification accuracy. The simulation results demonstrate the accuracy and efficiency of the proposed model in the IEEE 33-node distribution system.",

keywords = "correlation, deep learning, Distribution system topology identification, renewable energy",

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

note = "Funding Information: The work of H. Wu is partially supported by Teaching Postgraduate Studentship (TPS) Scheme of Hong Kong Polytechnic University. The work of M. Wang is partially supported in part by 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.; 2nd IEEE China International Youth Conference on Electrical Engineering, CIYCEE 2021 ; Conference date: 15-12-2021 Through 17-12-2021",

year = "2021",

month = dec,

doi = "10.1109/CIYCEE53554.2021.9676913",

language = "English",

series = "2021 IEEE 2nd China International Youth Conference on Electrical Engineering, CIYCEE 2021",

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

booktitle = "2021 IEEE 2nd China International Youth Conference on Electrical Engineering, CIYCEE 2021",

}

Wu, H, Xu, Z & Wang, M 2021, Convolutional Deep Leaning-Based Distribution System Topology Identification with Renewables. in 2021 IEEE 2nd China International Youth Conference on Electrical Engineering, CIYCEE 2021. 2021 IEEE 2nd China International Youth Conference on Electrical Engineering, CIYCEE 2021, Institute of Electrical and Electronics Engineers Inc., 2nd IEEE China International Youth Conference on Electrical Engineering, CIYCEE 2021, Chengdu, China, 15/12/21. https://doi.org/10.1109/CIYCEE53554.2021.9676913

Convolutional Deep Leaning-Based Distribution System Topology Identification with Renewables. / Wu, Huayi; Xu, Zhao; Wang, Minghao.
2021 IEEE 2nd China International Youth Conference on Electrical Engineering, CIYCEE 2021. Institute of Electrical and Electronics Engineers Inc., 2021. (2021 IEEE 2nd China International Youth Conference on Electrical Engineering, CIYCEE 2021).

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

TY - GEN

T1 - Convolutional Deep Leaning-Based Distribution System Topology Identification with Renewables

AU - Wu, Huayi

AU - Xu, Zhao

AU - Wang, Minghao

N1 - Funding Information: The work of H. Wu is partially supported by Teaching Postgraduate Studentship (TPS) Scheme of Hong Kong Polytechnic University. The work of M. Wang is partially supported in part by 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 - 2021/12

Y1 - 2021/12

N2 - Obtaining the distribution system topology states timely is critical for system monitoring while challenged by correlations brought by high penetrated renewable energy sources (RES). To address this issue, a deep learning model is proposed for distribution system topology identification considering the underlying complex correlations of renewables. Specifically, to remove the dependence of the power system model parameters like line impedance, the input of the model only consists of the voltage magnitudes. Then, this is fed into the proposed Convolutional deep learning model (CDLM), which can fully capture the data features and thus classify the topology of the grid to hedge against the correlations of the RES and thus enhance the identification accuracy. The simulation results demonstrate the accuracy and efficiency of the proposed model in the IEEE 33-node distribution system.

AB - Obtaining the distribution system topology states timely is critical for system monitoring while challenged by correlations brought by high penetrated renewable energy sources (RES). To address this issue, a deep learning model is proposed for distribution system topology identification considering the underlying complex correlations of renewables. Specifically, to remove the dependence of the power system model parameters like line impedance, the input of the model only consists of the voltage magnitudes. Then, this is fed into the proposed Convolutional deep learning model (CDLM), which can fully capture the data features and thus classify the topology of the grid to hedge against the correlations of the RES and thus enhance the identification accuracy. The simulation results demonstrate the accuracy and efficiency of the proposed model in the IEEE 33-node distribution system.

KW - correlation

KW - deep learning

KW - Distribution system topology identification

KW - renewable energy

UR - https://www.scopus.com/pages/publications/85125078954

U2 - 10.1109/CIYCEE53554.2021.9676913

DO - 10.1109/CIYCEE53554.2021.9676913

M3 - Conference article published in proceeding or book

AN - SCOPUS:85125078954

T3 - 2021 IEEE 2nd China International Youth Conference on Electrical Engineering, CIYCEE 2021

BT - 2021 IEEE 2nd China International Youth Conference on Electrical Engineering, CIYCEE 2021

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2nd IEEE China International Youth Conference on Electrical Engineering, CIYCEE 2021

Y2 - 15 December 2021 through 17 December 2021

ER -

Wu H, Xu Z, Wang M. Convolutional Deep Leaning-Based Distribution System Topology Identification with Renewables. In 2021 IEEE 2nd China International Youth Conference on Electrical Engineering, CIYCEE 2021. Institute of Electrical and Electronics Engineers Inc. 2021. (2021 IEEE 2nd China International Youth Conference on Electrical Engineering, CIYCEE 2021). doi: 10.1109/CIYCEE53554.2021.9676913

Convolutional Deep Leaning-Based Distribution System Topology Identification with Renewables

Abstract

Publication series

Conference

UN SDGs

Keywords

ASJC Scopus subject areas

More information

Other files and links

Fingerprint

Cite this