Scalable quality of service across multiple domains

Several state-less scheduling protocols have been proposed in the literature that achieve the same level of quality of service as state-full protocols. Thus, the scheduling accuracy of state-full protocols is combined with the scalability of state-less protocols. However, these new protocols treat each flow as an independent unit. In this paper, we present a state-less scheduling protocol that aggregates flows together in order to increase the number of flows that can be accepted into the network without violating their delay requirements. In addition, we present a state-less signaling protocol that may be used in combination with our state-less scheduling protocol. Contrary to sampling techniques, our signaling protocol is accurate yet requires only a constant amount of state at each node. Finally, our protocols can be used across multiple core networks.