Abstract:
We study the possibility to organize a solution in a network of arbitrary structure for a given set of interacting tasks with fault- and transient-fault-tolerance characteristics specified for each problem. For each problem, we distinguish a complex where all computers solve copies of this task (task replication), exchange results, and choose the correct one. The key problem in such computations is system mutual information agreement (SMIA) that ensures coherence of system information in all computers of all complexes under admissible faults. We derive sufficient structural conditions for reaching such a MIA and methods for finding them. We propose an algorithm for distinguishing complexes corresponding to problems being solved in computer networks (if at all possible).