Multicasting for multimedia applications
IEEE INFOCOM '92 Proceedings of the eleventh annual joint conference of the IEEE computer and communications societies on One world through communications (Vol. 3)
A source-based algorithm for delay-constrained minimum-cost multicasting
INFOCOM '95 Proceedings of the Fourteenth Annual Joint Conference of the IEEE Computer and Communication Societies (Vol. 1)-Volume - Volume 1
Research: An efficient adaptive routing algorithm for a network management system
Computer Communications
Guest Editorial Network Support for Multipoint Communication
IEEE Journal on Selected Areas in Communications
Multipoint communication: a survey of protocols, functions, and mechanisms
IEEE Journal on Selected Areas in Communications
Evaluation of multicast routing algorithms for real-time communication on high-speed networks
IEEE Journal on Selected Areas in Communications
Routing of multipoint connections
IEEE Journal on Selected Areas in Communications
Hi-index | 0.24 |
As real-time applications requiring dynamic group communication emerges, existing multicast routing algorithms must be improved to cater for high-speed routing decisions. Most of the reported efficient multicast routing algorithms for real-time applications construct a multicast tree using the Dijkstra's algorithm. However, they require reconstruction of the tree when there are group membership changes or faulty links/nodes in the session. In this paper, a dynamic routing strategy that does not rely on the construction of the multicast tree is presented. It is based on the ''clustering technique'' and it lends well for VLSI implementation. The Cluster Unit was implemented using VHDL and a suitable architecture for the routing strategy has been proposed. Performance evaluations based on software simulations show that the proposed routing strategy performs better than the most widely used multicast routing algorithm when the number of nodes become large. Moreover, performance comparisons based on the VHDL implementation of the Cluster Unit show that the proposed technique performs significantly better when realised in VLSI.