Exploiting structural similarity in network reliability analysis using graph learning

Abstract

Considering the large-scale networks that can represent construction of components in a unit, a transportation system, a supply chain, a social network system, and so on, some nodes have similar topological structures and thus play similar roles in the network and system analysis, usually complicating the analysis and resulting in considerable duplicated computations. In this paper, we present a graph learning approach to define and identify structural similarity between the nodes in a network or the components in a network system. Based on the structural similarity, we investigate component clustering at various significance levels that represent different extents of similarity. We further specify a spectral-graph-wavelet based graph learning method to measure the structural similarity and present its application in easing computation load of evaluating system survival signature and system reliability. The numerical examples and the application show the insights of structural similarity and effectiveness of the graph learning approach. Finally, we discuss potential applications of the graph-learning based structural similarity and conclude that the proposed structural similarity, component clustering, and graph learning approach are effective in simplifying the complexity of the network systems and reducing the computational cost for complex network analysis.

Discussion of signature‐based models of preventive maintenance

“…5 Structural information can also be utilized to perform semi-supervised clustering. 6 Each cluster corresponds to one type, and then we can calculate the survival signature. Note that we do not need to provide the signature-based formulation at each decision-making point, as it is mainly for interpretation, not for decision making.…”

“…For example, one could group all the components' remaining useful lifetime distributions into a few clusters using, for example, functional data clustering 5 . Structural information can also be utilized to perform semi‐supervised clustering 6 . Each cluster corresponds to one type, and then we can calculate the survival signature.…”

Exploring the vulnerability of transportation networks by entropy: A case study of Asia–Europe maritime transportation network

“…When the city (port, or station) is regarded as a node and the connection (transportation) between them is regarded as a connecting edge, such a complex system can be modeled by complex network to better understand its characteristics [4,5]. By exploring this kind of complex system through the lens of network science, several structural properties can be better understood, such as the reliability [6,7], resilience [8,9], safety [10,11],…”