Cluster-event biasing in Monte Carlo applications to systems reliability

Michael Khazen, Arie Dubi

Research output: Contribution to journalArticlepeer-review

3 Scopus citations


Estimation of the probabilities of rare events with significant consequences, e.g., disasters, is one of the most difficult problems in Monte Carlo applications to systems engineering and reliability. The Bernoulli-type estimator used in analog Monte Carlo is characterized by extremely high variance when applied to the estimation of rare events. Variance reduction methods are, therefore, of importance in this field. The present work suggests a parametric nonanalog probability measure based on the superposition of transition biasing and forced events biasing. The cluster-event model is developed providing an effective and reliable approximation for the second moment and the benefit along with a methodology of selecting near-optimal biasing parameters. Numerical examples show a considerable benefit when the method is applied to problems of particular difficulty for the analog Monte Carlo method. The suggested model is applicable for reliability assessment of stochastic networks of complicated topology and high redundancy with component-level repair (i.e., repair applied to an individual failed component while the system is operational).

Original languageEnglish
Pages (from-to)272-287
Number of pages16
JournalNuclear Science and Engineering
Issue number3
StatePublished - 1 Jan 2002
Externally publishedYes

ASJC Scopus subject areas

  • Nuclear Energy and Engineering


Dive into the research topics of 'Cluster-event biasing in Monte Carlo applications to systems reliability'. Together they form a unique fingerprint.

Cite this