On the Marshall–Olkin Copula Model for Network Reliability Under Dependent Failures

Abstract

The Marshall-Olkin (MO) copula model has emerged as the standard tool for capturing dependency between components in failure analysis in reliability. In this model shocks arise at exponential random times, that affect one or several components inducing a natural correlation in the failure process. However, because the number of parameter of the model grows exponentially with the number of components, MO suffers of the "curse of dimensionality". MO models are usually intended to be applied to design a network before its construction, therefore it is natural to assume that only partial information about failure behavior can be gathered, mostly from similar existing networks. To construct such a MO model, we propose an optimization approach to define the shock's parameters in the MO copula, in order to match marginal failures probabilities and correlations between these failures. To deal with the exponential number of parameters of this problem, we use a column-generation technique. We also discuss additional criteria that can be incorporated to obtain a suitable model. Our computational experiments show that the resulting MO model produces a close estimation of the network reliability, especially when the correlation between component failures is significant. Index TermsReliability, copula theory, optimization methods, failure analysis, network design.O. Matus, J. Barrera and E. Moreno are with the Faculty of Engineering and Sciences, Universidad Adolfo Ibáñez, Santiago, Chile. G. Rubino is with INRIA Rennes -Bretagne Atlantique, Rennes, France.

Efficient Estimation of Stochastic Flow Network Reliability

“…Also, another interesting venue of work is to tackle models with dependency among the links' states (which, as works such as [23] explain, can have an important impact in reliability values). In particular, it seems possible to apply the proposed method to cases where the dependence can be represented by a set of exponential random variables, like the case of the Marshall-Olkin copula distributions (arising from shock -and anti-shock-models with exponential time arrivals), which have been studied in the case of traditional network reliability in [24], [25] and [26], and can be extended to multi-level link capacity distributions. , 2009), and co-authored several of its chapters.…”

Limit distributions of the upper order statistics for the Lévy-frailty Marshall-Olkin distribution

“…In some real-world situations, the nature of the problem can lead to natural simplifications that reduce the number of parameters, e.g., in portfolio-credit risks or in insurance; see [3]. In this line, [24] propose a Lasso selection model to obtain the parameters. Another way to address the explosive number of parameters is to impose exchangeability of the components' lifetimes, as is the case of the LFMO model proposed by [17] and that we will discuss in detail in Section 2.…”

Communication Network Reliability under geographically correlated failures using Probabilistic Seismic Hazard Analysis

“…The strong correlations these faults show made them unsuited for analysis under the independent failures assumption. If independence is assumed, it tends to overestimate the reliability [13] and could lead to less reliable designs [14]. As communication networks are undoubtedly an essential part of the critical infrastructure, their proper functioning in post-disaster periods is crucial.…”