Using Game Theory to Solve the Fault Diagnosis Problem under Symmetric Comparison Rules

In this paper, we contribute in solving the system-level fault diagnosis (SLD) problem under the symmetric invalidation rules. The SLD aims at determining faulty nodes based on an input syndrome that is generated comparing the outputs from the different nodes. The symmetric comparison diagnosis model assumes that tasks are assigned to pairs of nodes and the results of executing these tasks are compared. Fault nodes are identified based on the agreements and disagreements among the nodes' outputs. A limit t is assumed on the maximum number of nodes that can fail simultaneously. Various diagnosis algorithms have been developed in the last decades, but the problem of efficiently identifying the set of faulty units of a diagnosable system remained an outstanding research issue. This work introduces a new diagnosis approach for the symmetric-based comparison diagnosis problem using game theory. In this approach, faulty nodes are identified by maximizing the payoffs of all players (nodes). We have tested the new diagnosis approach using randomly generated diagnosable systems under even extreme faulty situations in which the limit t was set close to the number of nodes. The extensive simulations we have conducted proved the efficiency of the new game-theory-based diagnosis algorithm as it succeeded in guessing the fault status all nodes in all faulty situations.