|Table of Contents|

PID Congestion Control Based on Back Propagation Neural Network in Ad Hoc Network

《南京理工大学学报》(自然科学版)[ISSN:1005-9830/CN:32-1397/N]

Issue:
2010年05期
Page:
628-635
Research Field:
Publishing date:

Info

Title:
PID Congestion Control Based on Back Propagation Neural Network in Ad Hoc Network
Author(s):
CHEN Liang12ZHANG Hong1LIU Feng-yu1
1.School of Computer Science and Technology,NUST,Nanjing 210094,China;2.Information Department,Nantong Textile Vocational Technology College,Nantong 226007,China
Keywords:
Ad Hoc network congestion control back propagation neural network proportional integral derivative
PACS:
TN929.5
DOI:
-
Abstract:
To improve the dynamic performance of the proportional integral derivative(PID) control and the optimize PID control parameter tuning in the Ad Hoc network active queue management(AQM),this paper proposes an AQM scheme about the PID congestion control based on the back propagation neural network(BPNN).Packet losses are divided into congestion loss and wireless loss in Ad Hoc network.Taking the arrival and loss packets as fluids,the stochastic differential relation between congestion windows and queue lengths is deduced.An AQM congestion control model in Ad Hoc network is proposed through small perturbations and linearized theory.The PID queue controller based on the BPNN is designed on the basis of the model.The algorithm can make adaptive adjustments to the controller PID coefficients according to the network situation.MATLAB and network simulator simulations indicate that the new algorithm is superior to the PID in rapidity of convergence and queue oscillation under the Ad Hoc network sudden flow,time-varying link capacity and delay condition.

References:

[ 1] 孙利民, 李波, 周新运. 无线传感器网络的拥塞控制技术[ J]. 计算机研究与发展, 2008, 45( 1): 63- 72.
[ 2] 陆锦军, 王执铨. 基于智能管理缓冲区的网络拥塞控制算法[ J]. 南京理工大学学报(自然科学版), 2006, 30( 5) : 573- 607.
[ 3] 续欣, 汤凯, 马刈非. 无线误码信道上的拥塞控制策略[ J]. 通信学报, 2004, 25( 12): 8- 13.
[ 4] Zheng F, Ne lson J. An Happroach to cong estion contro l design fo r AQM rou ters suppo rting TCP flow s in w ire less access netwo rks[ J]. Compu ter Ne tw orks, 2007, 51( 6): 1684- 1704.
[ 5] 王建新, 荣亮. 大时滞网络拥塞控制器的设计[ J]. 电子学报, 2007, 35( 11): 2105- 2110.
[ 6] A lH amm our i A, Liberatore V, B ranicky M, e t a.l Com plete stability reg ion charac teriza tion fo r PIAQM [ J] . ACM SIGBED Rev iew, 2006, 3( 2): 1- 6.
[ 7] XuW Q, Wu T J. TCP issues in m ob ile ad hoc ne t wo rks: Challenges and solutions[ J]. Journa l o f Computer Science and Technology, 2006, 21( 1): 72- 81.
[ 8] M israV, GongW B, Tow sley D. Fluibased ana lysis o f a network o fAQM rou ters supporting TCP flow s w ith an app lication to RED[ J]. ACM SIGCOMM Com puter Comm un ication Rev iew, 2000, 30( 4) : 151- 160.
[ 9] H o llo t C, M israV, Towsley D, et a.l A contro l theoretic analysis of RED [ A ]. Proceed ings of the IEEE INFOCOM[ C]. Anchorage: IEEE Press, 2001: 1510- 1519.
[ 10] 任丰原, 林闯, 任勇, 等. 大时滞网络中的拥塞控制算法[ J]. 软件学报, 2003, 14( 3): 503- 511.
[ 11] Budh ira ja A, H ernandezCam pos F, Ku lkarn iV G, et a.l Stochastic d iffe rentia l equation fo r TCP w indow size: Ana lys is and expe rim en tal va lidation[ J]. Probability in the Eng ineer ing and In fo rm ational Sc iences, 2004, 18( 1) : 111- 140.
[ 12] 柯志亨, 程荣祥, 邓德隽. NS2仿真实验- 多媒体和无线网络通信[M ]. 北京: 电子工业出版社, 2009: 235- 243.
[ 13] Ba rberaM, Lom ba rdo A, Schembra G. A flu idbased model of tim elim ited TCP flow s[ J]. Compu ter Ne t wo rks, 2004, 44( 3): 275- 288.
[ 14] Lindley D V. The theory o f queuesw ith a sing le se rver [ J] . M athem atica l Proceed ing s of the Cam bridge Ph ilosoph ical Soc iety, 1952, 48( 2): 277- 289.
[ 15] H ollo t C, M isra V, Tow sley D, et a.l Analysis and design of controllers for AQM routers supporting TCP flow s[ J]. IEEE Transactions on Autom a tic Contro,l 2002, 47( 6): 945- 959.
[ 16] M an Z H, W u H R, L iu S, et a.l A new adaptive back propaga tion a lgo rithm based on Lyapunov stability theo ry for neura l netwo rks[ J]. IEEE Transactions on N eural Netwo rks, 2006, 17( 6): 1580- 1591.
[ 17] 金忠, 胡钟山, 杨静宇. 基于BP神经网络的人脸识别方法[ J]. 计算机研究与发展, 1999, 36( 3 ): 274 - 277.
[ 18] 王文剑. BP神经网络模型的优化[ J] . 计算机工程与设计, 2000, 21( 6): 8- 10.
[ 19] 柯志亨. NS2教学手册[ EB /OL]. http: / /hpds. ee. ncku. edu. tw /~ sm allko /ns2 /ns2. htm, 2009 - 06 - 15 /2009- 06- 28.

Memo

Memo:
-
Last Update: 2012-11-02