A new scalable reliable multicast transport protocol using perfect buffer management

Abstract

Hierarchical reliable multicast transport protocols partition group members into local groups and allocate one local repair node for each local group to distribute the task of detecting and recovering lost packets. This repair node uses the data stored in its buffer to retransmit the requested packets to the requesting receivers. The problem is that they keep these packets for a long time until they get acknowledgments from all their children receivers of correctly receiving these packets. Keeping these packets creates a congestion problem which decreases the network throughput. This paper proposes a new scheme to solve this problem, by distributing the required packets between the repair node which we call it here the control receiver and some selected receives that have already received these packets correctly. The distribution of the packets decreases the number of packets in the repair node buffer, thus solve the congestion problem and increase the network throughput.