Network reliability analysis through survival signature and machine learning techniques

Publikation: Beitrag in FachzeitschriftArtikelForschungPeer-Review

Forschungs-netzwerk anzeigen

Details

OriginalspracheEnglisch
Aufsatznummer109806
FachzeitschriftReliability engineering & system safety
Jahrgang242
Frühes Online-Datum11 Nov. 2023
PublikationsstatusVeröffentlicht - Feb. 2024

Abstract

As complex networks become ubiquitous in modern society, ensuring their reliability is crucial due to the potential consequences of network failures. However, the analysis and assessment of network reliability become computationally challenging as networks grow in size and complexity. This research proposes a novel graph-based neural network framework for accurately and efficiently estimating the survival signature and network reliability. The method incorporates a novel strategy to aggregate feature information from neighboring nodes, effectively capturing the response flow characteristics of networks. Additionally, the framework utilizes the higher-order graph neural networks to further aggregate feature information from neighboring nodes and the node itself, enhancing the understanding of network topology structure. An adaptive framework along with several efficient algorithms is further proposed to improve prediction accuracy. Compared to traditional machine learning-based approaches, the proposed graph-based neural network framework integrates response flow characteristics and network topology structure information, resulting in highly accurate network reliability estimates. Moreover, once the graph-based neural network is properly constructed based on the original network, it can be directly used to estimate network reliability of different network variants, i.e., sub-networks, which is not feasible with traditional non-machine learning methods. Several applications demonstrate the effectiveness of the proposed method in addressing network reliability analysis problems.

ASJC Scopus Sachgebiete

Zitieren

Network reliability analysis through survival signature and machine learning techniques. / Shi, Yan; Behrensdorf, Jasper; Zhou, Jiayan et al.
in: Reliability engineering & system safety, Jahrgang 242, 109806, 02.2024.

Publikation: Beitrag in FachzeitschriftArtikelForschungPeer-Review

Shi Y, Behrensdorf J, Zhou J, Hu Y, Broggi M, Beer M. Network reliability analysis through survival signature and machine learning techniques. Reliability engineering & system safety. 2024 Feb;242:109806. Epub 2023 Nov 11. doi: 10.1016/j.ress.2023.109806
Download
@article{b245e4ea052e40459536e0a444ada60a,
title = "Network reliability analysis through survival signature and machine learning techniques",
abstract = "As complex networks become ubiquitous in modern society, ensuring their reliability is crucial due to the potential consequences of network failures. However, the analysis and assessment of network reliability become computationally challenging as networks grow in size and complexity. This research proposes a novel graph-based neural network framework for accurately and efficiently estimating the survival signature and network reliability. The method incorporates a novel strategy to aggregate feature information from neighboring nodes, effectively capturing the response flow characteristics of networks. Additionally, the framework utilizes the higher-order graph neural networks to further aggregate feature information from neighboring nodes and the node itself, enhancing the understanding of network topology structure. An adaptive framework along with several efficient algorithms is further proposed to improve prediction accuracy. Compared to traditional machine learning-based approaches, the proposed graph-based neural network framework integrates response flow characteristics and network topology structure information, resulting in highly accurate network reliability estimates. Moreover, once the graph-based neural network is properly constructed based on the original network, it can be directly used to estimate network reliability of different network variants, i.e., sub-networks, which is not feasible with traditional non-machine learning methods. Several applications demonstrate the effectiveness of the proposed method in addressing network reliability analysis problems.",
keywords = "Adaptive framework, Graph-based neural network, Machine learning, Network reliability, Survival signature",
author = "Yan Shi and Jasper Behrensdorf and Jiayan Zhou and Yue Hu and Matteo Broggi and Michael Beer",
note = "This work is supported by the National Natural Science Foundation of China (Grant 52205252, and 72171194), and the National Natural Science Foundation of Sichuan Province (Grant 2023NSFSC0876). The first author would also thanks for the support of the Alexander von Humboldt Foundation of Germany.",
year = "2024",
month = feb,
doi = "10.1016/j.ress.2023.109806",
language = "English",
volume = "242",
journal = "Reliability engineering & system safety",
issn = "0951-8320",
publisher = "Elsevier Ltd.",

}

Download

TY - JOUR

T1 - Network reliability analysis through survival signature and machine learning techniques

AU - Shi, Yan

AU - Behrensdorf, Jasper

AU - Zhou, Jiayan

AU - Hu, Yue

AU - Broggi, Matteo

AU - Beer, Michael

N1 - This work is supported by the National Natural Science Foundation of China (Grant 52205252, and 72171194), and the National Natural Science Foundation of Sichuan Province (Grant 2023NSFSC0876). The first author would also thanks for the support of the Alexander von Humboldt Foundation of Germany.

PY - 2024/2

Y1 - 2024/2

N2 - As complex networks become ubiquitous in modern society, ensuring their reliability is crucial due to the potential consequences of network failures. However, the analysis and assessment of network reliability become computationally challenging as networks grow in size and complexity. This research proposes a novel graph-based neural network framework for accurately and efficiently estimating the survival signature and network reliability. The method incorporates a novel strategy to aggregate feature information from neighboring nodes, effectively capturing the response flow characteristics of networks. Additionally, the framework utilizes the higher-order graph neural networks to further aggregate feature information from neighboring nodes and the node itself, enhancing the understanding of network topology structure. An adaptive framework along with several efficient algorithms is further proposed to improve prediction accuracy. Compared to traditional machine learning-based approaches, the proposed graph-based neural network framework integrates response flow characteristics and network topology structure information, resulting in highly accurate network reliability estimates. Moreover, once the graph-based neural network is properly constructed based on the original network, it can be directly used to estimate network reliability of different network variants, i.e., sub-networks, which is not feasible with traditional non-machine learning methods. Several applications demonstrate the effectiveness of the proposed method in addressing network reliability analysis problems.

AB - As complex networks become ubiquitous in modern society, ensuring their reliability is crucial due to the potential consequences of network failures. However, the analysis and assessment of network reliability become computationally challenging as networks grow in size and complexity. This research proposes a novel graph-based neural network framework for accurately and efficiently estimating the survival signature and network reliability. The method incorporates a novel strategy to aggregate feature information from neighboring nodes, effectively capturing the response flow characteristics of networks. Additionally, the framework utilizes the higher-order graph neural networks to further aggregate feature information from neighboring nodes and the node itself, enhancing the understanding of network topology structure. An adaptive framework along with several efficient algorithms is further proposed to improve prediction accuracy. Compared to traditional machine learning-based approaches, the proposed graph-based neural network framework integrates response flow characteristics and network topology structure information, resulting in highly accurate network reliability estimates. Moreover, once the graph-based neural network is properly constructed based on the original network, it can be directly used to estimate network reliability of different network variants, i.e., sub-networks, which is not feasible with traditional non-machine learning methods. Several applications demonstrate the effectiveness of the proposed method in addressing network reliability analysis problems.

KW - Adaptive framework

KW - Graph-based neural network

KW - Machine learning

KW - Network reliability

KW - Survival signature

UR - http://www.scopus.com/inward/record.url?scp=85177987789&partnerID=8YFLogxK

U2 - 10.1016/j.ress.2023.109806

DO - 10.1016/j.ress.2023.109806

M3 - Article

VL - 242

JO - Reliability engineering & system safety

JF - Reliability engineering & system safety

SN - 0951-8320

M1 - 109806

ER -

Von denselben Autoren