On network resource management for end-to-end QoS

This article examines issues and challenges in building distributed Quality-of-Service (QoS) architectures. We consider architectures that facilitate cooperation between the applications and the network so as to achieve the following tasks. Applications are allowed to express in their own language their QoS (performance and cost) requirements. These application-specific, requirements are communicated to the network in a language the network understands. Resources are appropriately allocated within the network so as to satisfy these requirements in an efficient, scalable, and reliable manner. Furthermore, the applications and the network have to cooperate "actively" (or continually) to be able to achieve these tasks under time-varying conditions.