MCD: An End-to-End Multicast Congestion Detection Scheme Using Support Vector Machines

Congestion is one of the most important issues impeding the development and deployment of IP multicast and multicast application. In this paper, the authors propose MCD, an end-to-end multicast congestion detection scheme with support vector machines. They focus on using support vector machines to detect incipient congestion in an end-to-end multicast network after training by using structural information about the multicast network. In this way, by using a learning system, they can predict incipient congestion in advance instead of waiting for packet loss.