Identifying critical nodes in the power grid via deep learning methods

Min Zhang; Zesan Liu; Chenghua Fu; Aijun Wen; Zhenya Wang; Wenjuan Zhang

doi:10.1117/12.3024227

13 May 2024 Identifying critical nodes in the power grid via deep learning methods

Min Zhang, Zesan Liu, Chenghua Fu, Aijun Wen, Zhenya Wang, Wenjuan Zhang

Proceedings Volume 13159, Eighth International Conference on Energy System, Electricity, and Power (ESEP 2023); 131597U (2024) https://doi.org/10.1117/12.3024227
Event: Eighth International Conference on Energy System, Electricity and Power (ESEP 2023), 2023, Wuhan, China

Abstract

Critical nodes play a pivotal role in ensuring the security and reliability of power grids, given that attacking them can lead to widespread power outages. Consequently, identifying critical nodes within the power grid holds immense significance. However, prior research either focuses on a single node metric or subjectively assigns weights to multiply metrics, resulting in inaccurate ranking lists. To overcome these limitations, this paper introduces the CGA algorithm to identify critical nodes in the power grid using deep learning methods. Specifically, CGA employs the contraction algorithm to establish feature matrices and utilizes the Susceptible-Infectious-Recovered (SIR) model to generate labels for nodes. Subsequently, CGA leverages the Convolutional Neural Network (CNN) to encode node information, effectively reducing computational complexity, then applies the Graph Neural Network (GNN) with an attention mechanism to learn node hidden representation. In addition, this paper employs two evaluation metrics to assess the effectiveness and distinguishability of CGA, including Kendall’s tau correlation coefficient and monotonicity index. Through conducting extensive experiments on the three datasets, simulation results demonstrate that CGA performs better than the six baseline algorithms, in which the effectiveness of identifying critical nodes is improved and the distinguishability of the ranking list is enhanced.

(2024) Published by SPIE. Downloading of the abstract is permitted for personal use only.

Citation Download Citation

Min Zhang, Zesan Liu, Chenghua Fu, Aijun Wen, Zhenya Wang, and Wenjuan Zhang "Identifying critical nodes in the power grid via deep learning methods", Proc. SPIE 13159, Eighth International Conference on Energy System, Electricity, and Power (ESEP 2023), 131597U (13 May 2024); https://doi.org/10.1117/12.3024227

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available