Transport Layer Statistical Multicast Based on the XTP Bucket Algorithm

Multicast or point-to-multipoint transmission is becoming a major issue for supporting distributed multimedia applications. In this paper, we analyze the service provided by theXtp reliable multicast. We discover several problems and drawbacks, such as multiple retransmission of the same data packets or the protocol inefficiency when performing with large group size and non-broadcast networks. To overcome some of these problems, we introduce new constraints at the sender side to prevent any unnecessary retransmissions. We introduce the service semantic calledstatistical reliable to cope with large group size while keeping a high level of reliability (related to error recovery issues). The quality of service provided by this modified protocol is assessed by simulation experiments for two different network environments :Fddi andAtm. We show that the reliability is almost binary, i.e. all reliable or unreliable at all. If the parameters are correctly sized, we can expect to get an all reliable semantic while using the statistical reliable protocol with the benefit of low protocol overhead. We are now working on a modified version of the proposed protocol to specifically adressAtm based networks.