Reliability Modeling of Mesh Storage Area Networks for Internet of Things

Abstract

With advances in Internet of Things (IoT), intelligent data sensors are being added to more and more devices that interact with human’s daily life in areas, such as medical services, smart grids, and financial services. IoT has made big contributions to data growth, requiring highly reliable data storage solutions. Storage area networks (SANs) are one of such solutions. To meet high reliability and availability requirements, SANs have to provide fault tolerance through redundancy to minimize or eliminate system downtime, thus preventing business discontinuity due to catastrophic events. Mesh is one of the common SAN topologies that have been applied to implement a fault tolerant SAN in practice. In this paper, failure behavior of a mesh SAN is modeled using a dynamic fault tree (DFT) in the case of perfect links, or a network graph in the case of imperfect links. Based on the constructed DFT or network graph model, reliability of the mesh SAN is evaluated using a binary decision diagram-based method. Results obtained from the case study can provide insights into the behavior of general mesh SAN systems, providing guidelines in the reliable design and operation of SANs.