|
On Providing Quality-of-Service Control for Core-Based Multicast Routing |
|
|
|
On Providing Quality-of-Service Control for Core-Based Multicast Routing |
|
The QoS considered in this project includes the end-to-end delay bound, the end-to-end inter-destination delay jitter bound, and the minimum guaranteed bandwidth. In the context of guaranteed QoS services, the requirement on the end-to-end delay bound for a flow will be translated into that on the minimal available bandwidth allocated to a flow.
The delay bound represents an upper bound on the acceptable end-to-end delay along any path from a source router to a destination router in the multicast group, while the inter-destination delay jitter bound gives the maximum difference that can be tolerated between the end-to-end delays along the paths from a source router to any two destination routers. Depending on the nature of applications, a user may require multicast services that fulfill a single QoS or a combination of several. The need for a bounded end-to-end delay and guaranteed bandwidth has been well justified in the open literature.
The situation in which a bounded inter-destination delay jitter among all the group members arises is also not rare. One possible scenario occurs during a teleconference in which any current speaker should be heard by all participants at approximately the same time to achieve the feeling of multi-party interactive face-to-face discussions. Another application domain is the distributed interactive simulation in which an inter-destination delay jitter bound is needed to constrain the time during which the simulation engines are in inconsistent states. A third application that requires a bounded inter-destination delay jitter is the receiver-driven layered multicast in which a multimedia application is encoded into a number of layers that can be incrementally combined to provide progressive refinement. The different layers of the hierarchical application are striped across multicast groups and receivers add/drop layers by joining/leaving the corresponding multicast groups. The constraint on the inter-destination delay jitter, combined with that on the delay, ensures that packets from all layers arrive at approximately the same time.
Return
to Project Homepage