摘要：

为实现对微流的最差延迟最早聚集，并对聚集完成的宏流进行过滤与排序，实现宏流公平调度，提出基于流量隔离的公平聚集器(FAFI)。FAFI解决了在基于流量聚集调度模式中，同一宏流内部各竞争微流之间的突发流量对数据包传输延迟产生影响的问题。通过严格的数学推理与演算，证明FAFI的有效性。仿真实验验证了对FAFI模型的定量分析结果和FAFI模型的性能。

关键词: 服务质量, 聚集器, 数据包调度, 公平, 延迟

Abstract:

This paper proposes a novel Fair Aggregator based on Flows Isolation(FAFI) that combines both Earliest Deadline First(EDF) scheduling and Worst-Case Fair Weighted Fair Queuing(WF2Q). By assembling individual flows in EDF and forwarding aggregated traffic in WF2Q, FAFI overcomes disadvantage in flow aggregating that the end-to-end delay of an individual flow is related to the burstiness of other flows sharing its aggregated traffic. An end-to-end delay bound is derived in the network equipped with proposed aggregator. A performance comparison is done with previous works on the aspects of end-to-end delay bound, network utilization, and scalability.

Key words: Quality of Service(QoS), aggregator, data packet scheduling, fairness, delay

中图分类号: 

• TP393.03