MODULE REPLACEMENT POLICY FOR DYNAMIC REDUNDANCY FAULT-TOLERANT COMPUTING SYSTEMS.

Fault-tolerant systems for critical applications include standby spares that are ready to replace active modules which fail to recover from the effects of a fault. A standby spare may also be used to replace a module suffering from frequent fault occurrences resulting in too many applications of the recovery process, in order to increase the computational availability. In this case a module replacement policy is needed. This policy will indicate upon occurrence of a module failure whether to retry the module or replace it considering mission time, probability of a system crash and computational availability. A module replacement policy for dynamic redundancy systems is presented and the improvement in computational availability due to its application is illustrated.