Coalitional games for a distributed signal enhancement application

We consider a scenario in which a number of sensor nodes monitor an area, where several sources are active. Each node has an interest to estimate the signal of a particular source using measurements that, unavoidably, are mixtures of the source signals. Nodes could improve the quality of the signal of interest if they were able to use the signals measured by other nodes, however, in a such a case, communication costs must be properly taken into account. To this end, coalitional game theory is used in our study. In the case where the communication cost is zero, we prove that the cooperation of all nodes is beneficial for all. In contrast, when the communication costs are taken into account, we employ a distributed merge-split coalition formation algorithm to organize the nodes into stable cooperative groups. Simulation results are in accordance with the theoretical findings.