区分服务下增强型动态RIO算法改进

鉴于区分网络中的标记算法和队列管理对服务公平性有很大影响,进行了基于增强型动态RIO(Enhanced Dynamic RED with In/Out bit,EDRIO)的确保服务下公平性的改进研究.首先从同构聚集流下的不同大小分组来分析各个分组间的公平性,然后从不同聚集流分配不同带宽来研究异构下的公平性.最后从数据包大小、目标速率及聚集流中包含的单流数量等进行性能仿真.实验结果表明,无论在同构还是异构下,基于EDRIO聚集流之间的公平性都比RIO和动态RIO聚集流之间的公平性好,而且该算法具有很好的扩展性.

An Improving Enhanced Dynamic RIO Algorithm for DiffServ

One of the more pop research issues in the context of Assured Forwarding(AF) is the fair distribution of bandwidth among aggregates sharing the same AF class.Marking algorithm and queue manager are very important for aggregates fairness.An improving enhanced dynamic RIO(EDRIO) algorithm from queue manager was proposed.The paper could not only analyze the fairness according to every packet's size under the homology of aggregates,but also study the fairness of heterogeneous flows in the case of every aggregate with a different bandwidth.The performances of the algorithm were simulated from packet size,target rate and the number of flows in aggregate.The several simulation experiments show that EDRIO is better than RIO for Assured Service in DiffServ networks and Dynamic RIO for Assured Service in DiffServ networks under the homology of aggregates and heterogeneous flows.The this algorithm has a better scalability.