On learning and the quality of service in a wireless network

The purpose of this paper is to study the quality of service and optimal distributed resource allocation in a wireless network. A wireless network is similar to the Internet in that the system description must allow for distributed resource allocation under uncertainty. The quality of service that results from the operation of a distributed system is analyzed in terms of a signal-to-noise model of a power-controlled wireless network. The method of analysis is game theory with learninig. Recently, the allocation of resources in the Internet has been studies using solution concepts based on learnabilility. The learnability in the context of a distributed mobile network is studied here. By the appropriate redefinition of the strategy spaces of the users, the resource allocation game, defined between the users, is learnable in the sense that eventually the users learn the optimal strategy concerning resource usage.