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.

The Distributed Queue Dual Bus (DQDB) proposal is the emerging candidate for the Metropolitan Area Network standard of the IEEE 802.6 committee. General properties of the DQDB access scheme such as fairness or priority issues are now well known. Therefore, different versions of the protocol have been released to address the existing problems. We develop a simple probabilistic model of the DQDB protocol under saturated condition in order to avoid excessive simulation runs. The model is based on a two step analysis taking into account the initial utilization state of the network. The accuracy of the model has been checked by comparaison with simulation and found to be very accurate. Moreover, we derive the fairness condition of the DQDB protocol and discuss some policies to achieve it.

In this paper we study the problem of flow control for LAN’s interconnected through a high speed MAN. We consider several input bridges feeding data through the MAN to an output bridge and specifically concern ourselves with the avoidance or minimization of buffer overflow at these bridges. We study the behavior of four flow control policies that differ from each other according to the type of information passed aroundamong the bridges. The most complex protocols use queue length information whereas the simpler protocols use either no information or packet age information. We show that the protocols using queue length information are optimal in the sense that they minimmize buffer overflow for a broad class of systems. In addition we compare the performance of these policies through a combination of analysis and simulation. We observe that using age information, which is relatively inexpensive to acquire, yields half of the benefit of queue length information. Furthermore, if most of the buffers are allocated to the output bridge, then there is little difference between the behavior of these policies. This suggests that simple protocols may work well under such allocations. Last, we study the issue of fairness when input bridges are not identical. We observe that the policies based on queue length information provide fairer treatment when the performance metric is probability of loss and the simple policies provide fairer treatment in the case of mean packet delay.

The main purpose of a Metropolitan Area Network is to provide High Speed transmission for both data and voice/video services. Users would share the MAN bandwidth through a dedicated interface based on a Distributed Queue Dual Bus (DQDB) algorithm of the IEEE 802.6 standard. A couple of important issues exists in the draft document of IEEE 802.6 standard, namely: fairness issue due to inherent propagation delay effect, causing non FIFO ordering among requests, bandwidth predictability issue, in this case, the bandwidth obtained by each node depends on the initial network utilization, priority mechanism is doubtful due to the two first points, This paper presents a comparative performance study of three versions of the DQDB protocol. Performance is measured in term of node throughput under saturated condition for several network parameters (number of stations, network size, initial network utilization, network speed). Our study is mainly based on simulation experiments. It is found that problems of fairness and bandwidth predictability, in the latest DQDB protocol (called the Bandwidth Balancing Mechanism - BBM), does not exist any longer. Finally, we discuss the gain provided by the different evolving releases and justify the motivation of the BBM and other bandwidth management policies with respect to the fairness issue.