Experimenting with Fuzzy Logic for QoS Management in Mobile Ad Hoc Networks

This paper describes a semi-stateless approach based on a fuzzy logic system for wireless mobile ad hoc networks. The proposed model, called FuzzyMARS, assures service differentiation delivery with low delay transmission. FuzzyMARS integrates a set of mechanisms: a fuzzy logic system for best-effort traffic regulation, three schemes for real-time traffic regulation, and an admission control mechanism for real-time traffic control. The architecture supports both real-time UDP traffic and best-effort UDP and TCP traffic. The use of fuzzy logic in wireless ad hoc networks, as simulations show, can add more flexibility and capability when operating with imprecise or instable information collected in an dynamic topology. The performance evaluation of the proposed model was studied under different mobility, channel, and traffic conditions. The results of simulations confirm that the proposed model can achieve a low and stable end-to-end delay under different network scalability and mobility conditions. Fuzzy logic techniques promise to be efficient tools for reducing delay transmission of multimedia applications in wireless ad hoc networks and deserve further attention and study.