EUVIMEDEUVIMED entdecken
Crossref

Prediction and mitigation of nonlocal cascading failures using graph neural networks

Bukyoung Jhun iD, Hoyun Choi iD, Yongsun Lee iD, Jongshin Lee iD, Cook Hyun Kim, B Kahng iD

Chaos: An Interdisciplinary Journal of Nonlinear Science · 01.01.2023 · 33 (1)

DOI: 10.1063/5.0107420 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Chaos: An Interdisciplinary Journal of Nonlinear Science, online erschienen am 09.01.2023. Verfasst von Bukyoung Jhun und 5 weiteren Autor:innen. Beteiligte Einrichtung: CCSS and CTP, Seoul National University, Seoul 08826, South Korea. Die Arbeit wurde bisher 16-mal zitiert (Crossref) und nennt 63 Literaturangaben. Gefördert von: National Research Foundation of Korea, KENTECH.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Cascading failures in electrical power grids, comprising nodes and links, propagate nonlocally. After a local disturbance, successive resultant can be distant from the source. Since avalanche failures can propagate unexpectedly, care must be taken when formulating a mitigation strategy. Herein, we propose a strategy for mitigating such cascading failures. First, to characterize the impact of each node on the avalanche dynamics, we propose a novel measure, that of Avalanche Centrality (AC). Then, based on the ACs, nodes potentially needing reinforcement are identified and selected for mitigation. Compared with heuristic measures, AC has proven to be efficient at reducing avalanche size; however, due to nonlocal propagation, calculating ACs can be computationally burdensome. To resolve this problem, we use a graph neural network (GNN). We begin by training a GNN using a large number of small networks; then, once trained, the GNN can predict ACs efficiently in large networks and real-world topological power grids in manageable computational time. Thus, under our strategy, mitigation in large networks is achieved by reinforcing nodes with large ACs. The framework developed in this study can be implemented in other complex processes that require longer computational time to simulate large networks.

Autor:innen und Institutionen

  • CCSS and CTP, Seoul National University, Seoul 08826, South Korea.
  • Center for Complex Systems and KI for Grid Modernization, Korea Institute of Energy Technology, Naju, Jeonnam 58217, South Korea.

ORCID-Profile: Bukyoung Jhun, Hoyun Choi, Yongsun Lee, Jongshin Lee, B Kahng

Förderung

  • National Research Foundation of Korea
  • KENTECH

Zitieren

APA

Jhun, B., Choi, H., Lee, Y., Lee, J., Kim, C. H., & Kahng, B. (2023). Prediction and mitigation of nonlocal cascading failures using graph neural networks. Chaos: An Interdisciplinary Journal of Nonlinear Science, 33(1). https://doi.org/10.1063/5.0107420

Vancouver

Jhun B, Choi H, Lee Y, Lee J, Kim CH, Kahng B. Prediction and mitigation of nonlocal cascading failures using graph neural networks. Chaos: An Interdisciplinary Journal of Nonlinear Science. 2023;33(1). doi:10.1063/5.0107420

BibTeX
@article{Jhun2023,
  author = {Jhun, Bukyoung and Choi, Hoyun and Lee, Yongsun and Lee, Jongshin and Kim, Cook Hyun and Kahng, B},
  title = {Prediction and mitigation of nonlocal cascading failures using graph neural networks},
  journal = {Chaos: An Interdisciplinary Journal of Nonlinear Science},
  year = {2023},
  volume = {33},
  number = {1},
  doi = {10.1063/5.0107420}
}
Kostenlos starten →