Learning based bandwidth management algorithms by using bargaining and fictitious play approaches

Nowadays, wireless networks have expanded significantly and being used by an increasing number of users to access multimedia information. However, wireless bandwidth is an extremely valuable and scarce resource. Therefore, efficient bandwidth management is a key factor to provide high-quality services in wireless/mobile multimedia networks. In this paper, we present a new bandwidth management scheme based on the market sharing game model. By using the fictitious play and Nash bargaining approach, the proposed model effectively formulates the competitive interaction situation between several access providers and their users. The main novelty of our proposed scheme is its self-adaptability for network dynamics and feasibility in providing a desirable solution. With a simulation study, it is confirmed that the proposed scheme can achieve better performance than other existing schemes under widely diverse network environments.