RAID 60 Storage Reliability and Cost Optimization Using Weibull Distribution and Cuckoo Search Algorithm with Lévy Flights

Abstract

This article describes how in this digital age, storage devices have been permitting the design of systems with the capacity to handle massive amount of diverse types of data. Real-time storage devices have been using complex architectures to accommodate the exponential increase of generated content. Hard drives have been at the core of most of storage systems. Estimating the reliability and the time to failure of such devices will be of great value. Weibull distribution has been widely used to assess the reliability of many systems. In this article, the three parameter Weibull distribution and Cuckoo search algorithm are combined to optimize the reliability and the maintenance cost of a RIAD 60 storage system. The numerical results show that using the proposed approach in this article, a RAID 60 system could reach its optimal reliable state by swapping less reliable drives by others more (used or new) reliable, whichever, is optimal according to the sought-after reliability threshold.