Efficient network QoS provisioning based on per node traffic shaping
IEEE/ACM Transactions on Networking (TON)
Determining end-to-end delay bounds in heterogeneous networks
Multimedia Systems - Special issue on the fifth workshop on network and operating system support for digital audio and video 1995 (NOSSDAV)
Hierarchical packet fair queueing algorithms
IEEE/ACM Transactions on Networking (TON)
Start-time fair queueing: a scheduling algorithm for integrated services packet switching networks
IEEE/ACM Transactions on Networking (TON)
Delay jitter bounds and packet scale rate guarantee for expedited forwarding
IEEE/ACM Transactions on Networking (TON)
Delay bounds for a network of guaranteed rate servers with FIFO aggregation
Computer Networks: The International Journal of Computer and Telecommunications Networking
Relationship between guaranteed rate server and latency rate server
Computer Networks: The International Journal of Computer and Telecommunications Networking
Network calculus: a theory of deterministic queuing systems for the internet
Network calculus: a theory of deterministic queuing systems for the internet
Per-domain packet scale rate guarantee for expedited forwarding
IWQoS'03 Proceedings of the 11th international conference on Quality of service
WF2Q: worst-case fair weighted fair queueing
INFOCOM'96 Proceedings of the Fifteenth annual joint conference of the IEEE computer and communications societies conference on The conference on computer communications - Volume 1
Hi-index | 0.00 |
Expedited Forwarding (EF) is a service defined under the Differentiated Services framework. Based on its recently revised definition in IETF RFC 3246, Packet Scale Rate Guarantee (PSRG) is its key construct, with which bounded nodal delay and edge-to-edge delay are provided. In this paper, we study the delay bound and PSRG for some EF networks. In these networks, each server belongs to a wide scheduler family which captures how much the server can be either late or earlier with respect to its reference fluid server. We show that edge-to-edge delay bound can be improved for EF networks of such servers. We also prove that PSRG can be derived from delay bound and call this PSRG-from-delay-bound property. With this property, we derive and discuss edge-to-edge PSRG for both a per-flow scheduling network and an aggregate scheduling network. In the derived results, delay bound and PSRG are a function of burstiness parameters of flows at the ingress edge. We hence further argue with analytical support that smoothing traffic at ingress edge can improve edge-to-edge delay bound and PSRG for the considered EF networks.