A novel rate adaptation structure for a scalable differentiated services architecture

The need to provide different service levels through the Internet has stimulated the research on differentiated services (DiffServ). This architecture is based on a set of mechanisms, deployed along an aggregated flow path, designed to offer differentiated treatments. Some approaches have appeared with the goal to decrease the implementation complexity of these mechanisms. C. L. Lee et al. have proposed a scalable architecture based on the DiffServ philosophy, where core routers do not need to support any specific function for service differentiation. In our work, we analyze, through simulation, the performance of that architecture regarding disordered packet loss. We also consider a different structure for queueing occupancy control that significantly reduces the rate of packet loss in the core of the domain. Therefore in our approach, the whole DiffServ functionality could efficiently be executed only in the edge routers, including the packet discard control function.