Network Reliability Assessment in a Random Environment S. O ¨ zekici, 1 R. Soyer 2 1 Department of Industrial Engineering, Koc ¸ University, 80910 Sarıyer-I ˙ stanbul, Turkey 2 Department of Management Science, The George Washington University, Washington, DC 20052 Received 7 May 2001; revised 3 September 2002; accepted 21 November 2002 DOI 10.1002/nav.10072 Abstract: In this paper we consider networks that consist of components operating under a randomly changing common environment. Our work is motivated by power system networks that are subject to fluctuating weather conditions over time that affect the performance of the network. We develop a general setup for any network that is subject to such environment and present results for network reliability assessment under two repair scenarios. We also present Bayesian analysis of network failure data and illustrate how reliability predictions can be obtained for the network. © 2003 Wiley Periodicals, Inc. Naval Research Logistics 50: 574 –591, 2003. in Wiley InterScience (www.interscience.wiley.com). DOI 10.1002/nav.10072 Keywords: network reliability; power systems; random environment; Bayesian analysis; Markov chain 1. INTRODUCTION AND OVERVIEW In this paper we consider networks that consist of components operating under a randomly changing common environment. Our work is motivated by power system networks that are subject to fluctuating weather conditions over time that effect the performance of the network. The affect of environmental conditions on reliability of power networks have been recognized in earlier papers by Gaver, Montmeat, and Patton [5] and Billinton and Bollinger [2], where the authors pointed out that power systems networks are exposed to fluctuating weather conditions and that the failure rates of equipment and lines increase during severe environmental condi- tions. These earlier papers proposed use of a two-state Markov model to describe normal and severe weather conditions and presented reliability results for parallel and series systems with small number of components. A more recent overview of these models and their extensions can be found in Billinton and Allan [1]. O ¨ zekici [12] discusses complex stochastic models where the deterministic and stochastic model parameters change randomly with respect to a randomly changing environmental factor. Thus, these parameters can be viewed as stochastic processes rather than simple deterministic Correspondence to: S. O ¨ zekici © 2003 Wiley Periodicals, Inc.