Cognitive Network Access using Fuzzy Decision Making

We consider a scenario in which wireless users want to connect to the Internet using one of several available network access opportunities, possibly using different radio technologies. We propose a distributed cognitive network access scheme with the aim of providing the best quality of service with respect to both radio link and core network performance and user application requirements. Knowledge of the service quality experienced by active connections is shared, and prospective users use Fuzzy Logic techniques to process cross-layer communication quality metrics and to estimate the expected transport-layer performance. These estimates are compared to the Quality of Service requirements of the application using Fuzzy Decision Making techniques to choose the most suitable access opportunity. This scheme naturally fits into the recently proposed Cognitive Network paradigm in that it defines a cognition process leveraging on end-to-end and cross-layer performance evaluation techniques as well as information sharing among users; moreover, it offers a significant amount of flexibility and extensibility, thanks to its modularity and its independence from the particular technology and application being used. The proposed scheme is shown to outperform state-of-the-art solutions in several multi-technology and multi-application scenarios, while at the same time achieving similar performance to application-specific omniscient schemes that we introduce in this paper as a benchmark.