Federations among sets of Cloud Providers (CPs), whereby a set of CPs agreeto mutually use their own resources to run the VMs of other CPs, are considereda promising solution to the problem of reducing the energy cost. In this paper,we address the problem of federation formation for a set of CPs, whose solutionis necessary to exploit the potential of cloud federations for the reduction ofthe energy bill. We devise a distributed algorithm, based on cooperative gametheory, that allows a set of CPs to cooperatively set up their federations insuch a way that their individual profit is increased with respect to the casein which they work in isolation, and we show that, by using our algorithm andthe proposed CPs' utility function, they are able to self-organize intoNash-stable federations and, by means of iterated executions, to adaptthemselves to environmental changes. Numerical results are presented todemonstrate the effectiveness of the proposed algorithm.
展开▼