Simplified Reliability Model Research Articles

Reliability model of the symmetric dual-node data processing system with functional redundancy

This scientific paper deals with the reliability model of the symmetric system based on two data processing nodes with the functional redundancy. The simplified reliability model of the system and the advanced model offered by the authors considering nonzero time of activation of the node primary functions, nonzero times for node failure detection and switching to the function backing-up mode are presented. The formulas for calculation of stationary availability factor, mean time to failure and mean time to repair are also discussed. Finally, the examples of reliability indices calculations according to the simplified and advanced reliability models are also given.

Reliability model of disk arrays RAID-5 with data striping

Within the scope of the this scientific paper, the simplified reliability model of disk arrays RAID-5 (redundant arrays of inexpensive disks) and an advanced reliability model offered by the authors taking into the consideration nonzero time of the faulty disk replacement and different failure rates of disks in normal state of the disk array and in degraded and rebuild states are discussed. The formula obtained by the authors for calculation of the mean time to data loss (MTTDL) of the RAID-5 disk arrays on basis of the advanced model is also presented. Finally, the technique of estimation of the initial reliability parameters, which are used in the reliability model, and the calculation examples of the mean time to data loss of the RAID-5 disk arrays for the different number of disks are also given.

Reliability model of fault-tolerant data processing system with primary and backup nodes

This paper deals with the fault-tolerant data processing systems, which are widely used in modern world of information technologies and have acceptable overhead expenses in hardware implementation. A simplified reliability model for duplex systems and the offered by authors advanced model for data processing systems with primary and backup nodes based on a three-state model of recoverable elements, which takes into consideration different failure rates of passive and active nodes and finite time of node activation, are also given. A calculation formula for the availability factor of the dual-node data processing system with primary and backup nodes and calculation examples are also provided.