基于双向压力模型的多源应用层组播拥塞控制方案

A Multi-Source ALM Congestion Control Method Based on Bi-Directional Pressure

相比传统组播模式,多源应用层组播能用更少的网络资源实现多方交互式应用.但组播特性、应用层环境以及多源属性均会使得多源应用层组播的拥塞问题变得更加严重.因此,提出一种基于双向压力模型的多源应用层组播拥塞控制方案,该方案采用正反压的方式来避免组播流在节点上产生拥塞,并同时采用基于权重的缓冲转移策略来保证同一组内所有数据源的组播流在共享节点上公平地占用缓冲和带宽资源,并进一步讨论了环形拥塞问题的严重性和解决办法.PlanetLab实验网评测结果表明,该方案在实现多源应用层组播拥塞控制的同时,能够协调不同组播流的流量,实现其公平性和可扩展性.

The multi-source ALM （application layer multicast） can achieve multi-party interaction applications with less resources compared with the traditional multicast method. But the multieast characters, the application layer environment and the properties of the multi-source will make the congestion control of ALM worse. So a multi-source ALM congestion control method based on bi- directional pressure is proposed in this paper. By calculating the forward pressure and the backward pressure for every flow on local node, all the flows according to its weight share the local buffers so as to improve utilization. The forward pressure accelerates the data transmission speed and the backward pressure decreases the data volume produced by the source. To release the congestion on the local node and achieve the control target, the method limits the data volume of different flows in the local buffer. The ring congestion problem, which is critical for the multi-source ALM, has also been discussed in this paper, and a simple method has been proposed. PlanetLab experiment is given to demonstrate that the proposed method can be used to control the congestion effectively, balance flows and buffers of all the sources and achieve fairness and scalability.