用于队列管理的模糊增益神经元自适应控制器

doi:10.13190/jbupt.201002.99.276

北京邮电大学学报 ›› 2010, Vol. 33 ›› Issue (2): 99-104.doi: 10.13190/jbupt.201002.99.276

用于队列管理的模糊增益神经元自适应控制器

汪浩田作华

(上海交通大学自动化系, 上海 200240)

收稿日期:2009-06-18 修回日期:2009-11-18 出版日期:2010-04-28 发布日期:2010-04-28
通讯作者: 汪浩
作者简介:汪浩(1986—)，男，博士生， Email: haowang.sjtu@gmail.com；田作华(1946—)，男，教授，博士生导师.
基金资助:
国家自然科学基金项目(60574081)

Adaptive Neuron Controller with Fuzzy SelfTuning Gain for Queue Management

WANG Hao, TIAN Zuo-hua

(Department of Automation, Shanghai Jiao Tong University, Shanghai 200240, China)

Received:2009-06-18 Revised:2009-11-18 Online:2010-04-28 Published:2010-04-28

摘要/Abstract

摘要：

针对具有参数时变及非线性特性的网络拥塞控制系统，提出了一种模糊增益神经元主动队列管理算法(FNAQM). 采用路由器队列长度及数据流速作为拥塞度量，在检测当前拥塞信息的同时，预测未来拥塞的状况. 结合神经元控制和模糊控制的优点，利用单神经元计算数据包标记概率，采用有监督的Hebb学习规则在线调整加权系数. 设计的模糊控制器可动态调整神经元增益，能获得更好的控制性能. FNAQM具有结构简单、易于实现、自适应能力强等优点. 仿真实验结果表明，FNAQM能快速将队列调整至目标值，并维持较小的队列抖动，对动态数据流和非响应流具有良好的鲁棒性.

关键词: 拥塞控制, 主动队列管理, 单神经元, 模糊自调整

Abstract:

In light of the congestion control system with timevarying parameters and nonlinear property, a neuron control algorithm with fuzzy selftuning gain (FNAQM) is proposed for active queue management. Both queue length and traffic rate are employed as congestion indicators which detect both current and incipient congestion states. Combining the advantages of neuron control and fuzzy control strategies, the endtoend mark probability is calculated by the neuron controller, in which the weights are adjusted online by supervisory Hebb learning rule. Additionally, fuzzy logic control is used to tune the gain of the neuron dynamically for improved network performance. The proposed scheme exhibits good adaptability and selflearning ability, being simple in form and easy to implement. Simulation in network simulator2(NS2) demonstrates that FNAQM can quickly stabilize the queue length to the target with small jitter, and shows strong robustness against dynamic traffics and nonresponsive flows. 

Key words: congestion control, active queue management, single neuron, fuzzy selftuning

汪浩田作华. 用于队列管理的模糊增益神经元自适应控制器[J]. 北京邮电大学学报, 2010, 33(2): 99-104.

WANG Hao TIAN Zuo-hua. Adaptive Neuron Controller with Fuzzy SelfTuning Gain for Queue Management[J]. JOURNAL OF BEIJING UNIVERSITY OF POSTS AND TELECOM, 2010, 33(2): 99-104.

参考文献

[1] Braden B, Clark D, Crowcroft J, et al. RFC2309—1998, Recommendations on queue management and congestion avoidance in the Internet[S]. New York: IETF, 1998: 1-17.
[2] Floyd S, Jacobson V. Random early detection gateways for congestion avoidance[J]. IEEE/ACM Transactions on Networking, 1993, 1(4): 397-413.
[3] Feng W C, Kang G Shin, Kandlur D, et al. The blue active queue management algorithms[J]. IEEE/ACM Transaction on Networking, 2002, 10(4): 513-528.
[4] Hollot C V, Misra V, Towsley D, et al. On designing improved controllers for AQM routers supporting TCP flows//Proceedings of IEEE Conference on Computer Communications. Alaska: , 2001:1726-1734.
[5] Ryu S, Rump C, Qiao Chunming. A predictive and robust active queue management for Internet congestion control//Proceedings of IEEE Symposium on Computers and Communications. Turkey: , 2003: 991-998.
[6] Kunniyur S, Srikant R. An adaptive virtual queue (AVQ) algorithm for active queue management[J]. IEEE/ACM Transactions on Networking, 2004, 12(2): 286-299.
[7] Athuraliya S, Low S H, Li V H, et al. REM: active queue management. IEEE Network, 2001, 15(3): 48-53.
[8] Chen Qiang, Yang O W W. Robust controller design for AQM router[J]. IEEE Transactions on Automatic Control, 2007, 52(5): 938-943.
[9] Cho Hyun C, Fadali Sami M, Lee Hyunjeong. Adaptive neural queue management for TCP networks[J]. Computer and Electrical Engineering, 2008, 34(6): 447-469.
[10] Manfredi S, di Bernardo M, Garofalo F. Design, validation and experimental testing of a robust AQM control[J]. Control Engineering Practice, 2009, 17(3): 394-407.
[11] 李国勇. 智能控制及其MATLAB实现[M]. 北京: 电子工业出版社, 2005.
[12] Hadjadj Aoul Y, Mehaoua A, Skianis C. A fuzzy logic-based AQM for real-time traffic over internet[J]. Computer Networks, 2007, 51(16): 4617-4633.
[13] 曾志民, 张天魁, 冯春燕, 等. 一种快速响应的AQM算法[J]. 北京邮电大学学报, 2005, 28(4): 5-9. Zeng Zhimin, Zhang Tiankui, Feng Chunyan, et al. An AQM scheme for fast response[J]. Journal of Beijing University of Posts and Telecommunications, 2005, 28(4): 5-9.
[14] Jacobson V. Congestion avoidance and control//Proceedings of ACM SIGCOMM, 1988. Stanford: , 1988: 314-329.

[1]	赵成林谭虎毛松. 利用路径优先级实现传感器网络中的拥塞避免[J]. 北京邮电大学学报, 2012, 35(1): 15-18.
[2]	李陶深，韦燕霞，葛志辉. 跨层负载感知的无线Mesh网络拥塞控制[J]. 北京邮电大学学报, 2011, 34(1): 50-54.
[3]	刘期烈李云潘英俊赵玲. 延迟容忍网络中基于复制率的拥塞控制算法[J]. 北京邮电大学学报, 2010, 33(4): 88-92.
[4]	赖峻, 叶梧, 冯穗力. QDB-AQM: 基于排队延时的网关拥塞控制设计[J]. 北京邮电大学学报, 2008, 31(5): 30-35.
[5]	朱小虎1, 曹阳1,2, 王力纬1. 采用多级拥塞控制的NOC路由算法[J]. 北京邮电大学学报, 2007, 30(5): 91-94.
[6]	徐伟强1, 2，汪亚明1，包晓安1, 陈积明2. MPCC: 一种用于Ad Hoc网络多径路由的优化拥塞控制算法[J]. 北京邮电大学学报, 2007, 30(5): 41-45.
[7]	王伟，高月红，杨大成. CDMA系统的自适应拥塞控制算法研究[J]. 北京邮电大学学报, 2006, 29(4): 69-72.
[8]	柳立峰，邹仕洪，张雷，程时端. 基于定向扩散的传感器网络拥塞与速率控制[J]. 北京邮电大学学报, 2006, 29(2): 90-93.
[9]	王晓利，纪红，乐光新，周鸿霞. 无线环境下保证QoS的传输层拥塞控制机制[J]. 北京邮电大学学报, 2005, 28(6): 26-29.
[10]	曾志民,张天魁,冯春燕,丁炜. 一种快速响应的AQM算法[J]. 北京邮电大学学报, 2005, 28(4): 5-9.
[11]	宋丽华,陈鸣,张睿. 一种基于测量的TCP Fast改进方案[J]. 北京邮电大学学报, 2005, 28(4): 27-31.
[12]	张晋豫１,孟洛明２,邱雪松２. 一个恒价的IP网络实时记费管理机制[J]. 北京邮电大学学报, 2005, 28(3): 68-71.
[13]	喻炜，杨放春. ATN传输层网关的研究[J]. 北京邮电大学学报, 2005, 28(3): 107-110.
[14]	姚凌，纪红，乐光新. 一种改进的无线TCP拥塞控制算法及〖JZ〗其稳态流量模型[J]. 北京邮电大学学报, 2005, 28(2): 42-45.
[15]	张志群,丁炜,武穆清. TCP/IP拥塞控制机制在MPLS网络中的#br# 改进及分析[J]. 北京邮电大学学报, 2002, 25(2): 93-97.

用于队列管理的模糊增益神经元自适应控制器

Adaptive Neuron Controller with Fuzzy SelfTuning Gain for Queue Management

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价