Risk Early Warning of Power Systems With Partial State Observations Based on the Graph Attention Neural Network

Qin Wang; Donghong Li; Xi Zhang; Xiujuan Fan

doi:10.1109/ISCAS46773.2023.10181351

Risk Early Warning of Power Systems With Partial State Observations Based on the Graph Attention Neural Network

Qin Wang
, Donghong Li
, Xi Zhang^*
, Xiujuan Fan

^*Corresponding author for this work

School of Automation

Beijing Institute of Technology
State Grid Information and Communication CO. LTD.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

1 Citation (Scopus)

Abstract

The fluctuations of loads and renewable power plants can make the power system operate without meeting the n-1 criterion. In this paper, we propose a node indispensability estimation (NIE) model based on the Graph Attention Network (GAT) for risk early warning. The existence of the indispensable component for specific operation conditions is predicted whose independent removal causes overloading. Considering the difficulty to place monitoring units on all system components, the state information of a part of the buses is used as input for the NIE model. The GAT is compared with other neural network algorithms such as Graph Convolutional Networks (GCN) and Multilayer Perceptron (MLP). Simulation results in IEEE test systems show that the proposed model based on GAT has sufficiently high prediction accuracies in estimating the node indispensability with partial state observations. Our work provides useful warnings for power operators to improve the system operation condition to secure sufficient safety levels.

Original language	English
Title of host publication	ISCAS 2023 - 56th IEEE International Symposium on Circuits and Systems, Proceedings
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	9781665451093
DOIs	https://doi.org/10.1109/ISCAS46773.2023.10181351
Publication status	Published - 2023
Event	56th IEEE International Symposium on Circuits and Systems, ISCAS 2023 - Monterey, United States Duration: 21 May 2023 → 25 May 2023

Publication series

Name	Proceedings - IEEE International Symposium on Circuits and Systems
Volume	2023-May
ISSN (Print)	0271-4310

Conference

Conference	56th IEEE International Symposium on Circuits and Systems, ISCAS 2023
Country/Territory	United States
City	Monterey
Period	21/05/23 → 25/05/23

UN SDGs

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

SDG 7 Affordable and Clean Energy

Keywords

Risk early warning
graph attention network
partial observation
power system

Access to Document

10.1109/ISCAS46773.2023.10181351

Cite this

Wang, Q., Li, D., Zhang, X., & Fan, X. (2023). Risk Early Warning of Power Systems With Partial State Observations Based on the Graph Attention Neural Network. In ISCAS 2023 - 56th IEEE International Symposium on Circuits and Systems, Proceedings (Proceedings - IEEE International Symposium on Circuits and Systems; Vol. 2023-May). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ISCAS46773.2023.10181351

Wang, Qin ; Li, Donghong ; Zhang, Xi et al. / Risk Early Warning of Power Systems With Partial State Observations Based on the Graph Attention Neural Network. ISCAS 2023 - 56th IEEE International Symposium on Circuits and Systems, Proceedings. Institute of Electrical and Electronics Engineers Inc., 2023. (Proceedings - IEEE International Symposium on Circuits and Systems).

@inproceedings{fbcbebbd63b740dfb45a103ffacc2048,

title = "Risk Early Warning of Power Systems With Partial State Observations Based on the Graph Attention Neural Network",

abstract = "The fluctuations of loads and renewable power plants can make the power system operate without meeting the n-1 criterion. In this paper, we propose a node indispensability estimation (NIE) model based on the Graph Attention Network (GAT) for risk early warning. The existence of the indispensable component for specific operation conditions is predicted whose independent removal causes overloading. Considering the difficulty to place monitoring units on all system components, the state information of a part of the buses is used as input for the NIE model. The GAT is compared with other neural network algorithms such as Graph Convolutional Networks (GCN) and Multilayer Perceptron (MLP). Simulation results in IEEE test systems show that the proposed model based on GAT has sufficiently high prediction accuracies in estimating the node indispensability with partial state observations. Our work provides useful warnings for power operators to improve the system operation condition to secure sufficient safety levels.",

keywords = "Risk early warning, graph attention network, partial observation, power system",

author = "Qin Wang and Donghong Li and Xi Zhang and Xiujuan Fan",

note = "Publisher Copyright: {\textcopyright} 2023 IEEE.; 56th IEEE International Symposium on Circuits and Systems, ISCAS 2023 ; Conference date: 21-05-2023 Through 25-05-2023",

year = "2023",

doi = "10.1109/ISCAS46773.2023.10181351",

language = "English",

series = "Proceedings - IEEE International Symposium on Circuits and Systems",

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

booktitle = "ISCAS 2023 - 56th IEEE International Symposium on Circuits and Systems, Proceedings",

address = "United States",

}

Wang, Q, Li, D, Zhang, X & Fan, X 2023, Risk Early Warning of Power Systems With Partial State Observations Based on the Graph Attention Neural Network. in ISCAS 2023 - 56th IEEE International Symposium on Circuits and Systems, Proceedings. Proceedings - IEEE International Symposium on Circuits and Systems, vol. 2023-May, Institute of Electrical and Electronics Engineers Inc., 56th IEEE International Symposium on Circuits and Systems, ISCAS 2023, Monterey, United States, 21/05/23. https://doi.org/10.1109/ISCAS46773.2023.10181351

Risk Early Warning of Power Systems With Partial State Observations Based on the Graph Attention Neural Network. / Wang, Qin; Li, Donghong; Zhang, Xi et al.
ISCAS 2023 - 56th IEEE International Symposium on Circuits and Systems, Proceedings. Institute of Electrical and Electronics Engineers Inc., 2023. (Proceedings - IEEE International Symposium on Circuits and Systems; Vol. 2023-May).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Risk Early Warning of Power Systems With Partial State Observations Based on the Graph Attention Neural Network

AU - Wang, Qin

AU - Li, Donghong

AU - Zhang, Xi

AU - Fan, Xiujuan

PY - 2023

Y1 - 2023

N2 - The fluctuations of loads and renewable power plants can make the power system operate without meeting the n-1 criterion. In this paper, we propose a node indispensability estimation (NIE) model based on the Graph Attention Network (GAT) for risk early warning. The existence of the indispensable component for specific operation conditions is predicted whose independent removal causes overloading. Considering the difficulty to place monitoring units on all system components, the state information of a part of the buses is used as input for the NIE model. The GAT is compared with other neural network algorithms such as Graph Convolutional Networks (GCN) and Multilayer Perceptron (MLP). Simulation results in IEEE test systems show that the proposed model based on GAT has sufficiently high prediction accuracies in estimating the node indispensability with partial state observations. Our work provides useful warnings for power operators to improve the system operation condition to secure sufficient safety levels.

AB - The fluctuations of loads and renewable power plants can make the power system operate without meeting the n-1 criterion. In this paper, we propose a node indispensability estimation (NIE) model based on the Graph Attention Network (GAT) for risk early warning. The existence of the indispensable component for specific operation conditions is predicted whose independent removal causes overloading. Considering the difficulty to place monitoring units on all system components, the state information of a part of the buses is used as input for the NIE model. The GAT is compared with other neural network algorithms such as Graph Convolutional Networks (GCN) and Multilayer Perceptron (MLP). Simulation results in IEEE test systems show that the proposed model based on GAT has sufficiently high prediction accuracies in estimating the node indispensability with partial state observations. Our work provides useful warnings for power operators to improve the system operation condition to secure sufficient safety levels.

KW - Risk early warning

KW - graph attention network

KW - partial observation

KW - power system

UR - https://www.scopus.com/pages/publications/85167705245

U2 - 10.1109/ISCAS46773.2023.10181351

DO - 10.1109/ISCAS46773.2023.10181351

M3 - Conference contribution

AN - SCOPUS:85167705245

T3 - Proceedings - IEEE International Symposium on Circuits and Systems

BT - ISCAS 2023 - 56th IEEE International Symposium on Circuits and Systems, Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 56th IEEE International Symposium on Circuits and Systems, ISCAS 2023

Y2 - 21 May 2023 through 25 May 2023

ER -

Wang Q, Li D, Zhang X, Fan X. Risk Early Warning of Power Systems With Partial State Observations Based on the Graph Attention Neural Network. In ISCAS 2023 - 56th IEEE International Symposium on Circuits and Systems, Proceedings. Institute of Electrical and Electronics Engineers Inc. 2023. (Proceedings - IEEE International Symposium on Circuits and Systems). doi: 10.1109/ISCAS46773.2023.10181351

Risk Early Warning of Power Systems With Partial State Observations Based on the Graph Attention Neural Network

Abstract

Publication series

Conference

UN SDGs

Keywords

Access to Document

Other files and links

Fingerprint

Cite this