基于模糊流感知的动态优先公平调度算法

邱恭安; 张顺颐; 胡隽

doi:10.3724/SP.J.1146.2007.00891

基于模糊流感知的动态优先公平调度算法

doi: 10.3724/SP.J.1146.2007.00891

邱恭安^{①;张顺颐},
张顺颐,
胡隽

基金项目:

国家863计划项目(2006AA01Z32)资助课题

计量
- 文章访问数: 2660
- HTML全文浏览量: 69
- PDF下载量: 730
- 被引次数: 0
出版历程
- 收稿日期: 2007-06-07
- 修回日期: 2007-10-12
- 刊出日期: 2009-02-19

Fuzzy Flow Awareness Based Dynamical Priority Fair Scheduling Algorithm

Qiu Gon-gan^{①;张顺颐},
Zhang Shun-yi,
Hu Jun

摘要

摘要: 为适应网络的动态性，提高调度公平性和资源效率，流感知优先公平调度机制需要动态的多业务区分转发。与链路负载状态相关的模糊流感知能够实现路径上的一致性业务区分，而基于模糊流感知的动态优先公平调度算法通过调整优先队列负载门限在流式流和弹性流之间实现转发优先权的动态交替，在链路轻载时实现不同流间的相对公平调度，在链路重载时则强调实时业务的绝对优先权以保证其时延要求。算法公平性分析和仿真计算显示提出算法的动态区分转发通过适度增加优先业务队长能够大幅度提高弹性流的接纳率，具有较高的链路平均吞吐量和资源效率。
- 流感知网络;模糊流感知;动态优先;公平调度
Abstract: Flow-awareness based priority fairness scheduling scheme will perform distinct forwarding policy dynamically for different traffic flows to adapt the network change and enhance the fairness of scheduling. The fuzzy flow-awareness with the load state information can identify different services congruously in path. And the dynamic priority fairness scheduling algorithm based on fuzzy flow-awareness will adjust the priority of forwarding dynamically between streaming flows and elastic flows by changing the threshold of priority queue. The algorithm emphasizes the fairness of scheduling under the light load and the priority of real-time applications under the heavy load for their delay requirements. The analysis of fairness and the results of simulation show that proposed algorithm could enhance the admission probability of elastic flows largely by increasing the priority queue length reasonably. At the same time, simulation shows that the algorithm has high the average throughput of link and the utility of resources.

HTML全文

参考文献(1)

Strassne J. Using autonomic principles to manage convergedservices in next generation networks. The Fourth IEEEInternational Workshop on Engineering of Autonomic andAutonomous Systems, Tucson, 26-29 March 2007: 176-186.[2]Oueslati S and Roberts J. A new direction for quality ofservice: flow-aware networking. Next Generation InternetNetworks, Rome, 18~20 April 2005: 226-232.[3]Kortebi A, Oueslati S, and Roberts J. Cross-protect: implicitservice differentiation and admission control. HighPerformance Switching and Routing (HPSR), Phoenix,Arizona, April 18 2004: 56-60.[4]Barakat C and Thiran P, et al.. Modeling Internet backbonetraffic at the flow level[J].IEEE Trans. on Signal Processing.2003, 51(8):2111-2124[5]Roberts J and Oueslati S. Quality of service by flow awarenetworking[J].Philosophical Trans. of The Royal Society ofLondon, series A.2000, 358(1773):2197-2207[6]Kortebi A, Muscariello L, and Oueslati S, et al.. Evaluatingthe number of active flows in a scheduler realizing fairstatistical bandwidth sharing. The ACM internationalconference on Measurement and modeling of computersystems (SIGMETRICS05), Banff, Canada, 6-10 June 2005:217-228.[7]Kortebi A, Oueslati S, and Roberts J. Implicit servicedifferentiation using deficit round robin. Proceedings of ITC19, Beijing, 29 August-2 September 2005.[8]Ashour M and Tho Le-Ngoc. Performance analysis ofweighted fair queues with variable service rates. InternationalConference on Digital Telecommunications ( ICDT '06), CapEsterel, 29-31 Aug. 2006: 51-56.[9]Jiang Y, Emstad P J, and Nevin A, et al.. Measurementbasedadmission control for a flow-aware network. NextGeneration Internet Networks [C], Rome, Italy, 18-20 April2005: 318-325.[10]王万良. 人工智能及其应用. 北京: 高等教育出版社, 2005:112-126.Wang Wan-liang. Artificial Intelligence and Application.Beijing: Higher education press, 2005: 112-126.[11]林闯, 单志广, 任丰原. 计算机网络的服务质量(QoS). 北京:清华大学出版社, 2004: 209-226.Lin Chuang, Shan Zhi-guang, and Ren Feng-yuan. Quality ofService of Computer Networks. Beijing: Tsinghua Universtitypress, 2004: 209-226.[12]Cho HC, Fadali MS, and Lee Hyunjeong. Dynamic queuescheduling using fuzzy systems for Internet routers. The 14thIEEE International Conference on Fuzzy Systems (FUZZ'05),Reno, USA, May 22-25 2005: 471-476.

施引文献

资源附件(0)

访问统计