基于滑模变结构控制的鲁棒AQM算法研究
|
摘要
随着信息化程度的日益提高,Internet技术已经与人们的生活息息相关。一方面网络用户的数量呈爆炸式的增长,另一方面出现了许多新业务如话音、图像等多媒体信息,并且实时多媒体流像电视会议、远程教学等也更加普遍。数据流的增加给网络带来的后果就是造成路由节点承担了很大的负担,势必对网络的服务质量造成了很大的影响,导致网络拥塞问题更加严重。
AQM算法是目前解决拥塞问题的有效方法,本文在已有AQM算法的基础上,提出了稳定性与鲁棒性强的几种队列管理算法,所做的主要工作如下：
(1)针对网络中存在负载数量和回路延时等不确定因素,提出了基于变结构控制的AQM算法,其中作为拥塞指示的切换函数是队列长度误差和输入速率与链路容量之差的线性组合,拥塞控制策略设计简单,易于实现,不依赖被控对象的模型,很好地解决了网络拥塞控制问题。用NS2网络仿真软件验证了VSC算法的性能,它不仅具有良好的队列稳定性和较小的队列延时,同时对网络环境的变化具有很强的鲁棒性。
(2)针对变结构控制中存在的抖振问题,提出了两种基于智能变结构的AQM算法FVSC、NVSC,其中FVSC算法和NVSC算法根据拥塞的状况,分别采用模糊推理算法和单神经元梯度学习算法,自适应调节控制器中的参数,它们继承了VSC算法鲁棒性强的优点同时减弱了VSC算法的抖振。仿真实验表明FVSC算法与NVSC算法保留了VSC算法的良好性能,并且在相同网络环境下队列稳定性、队列延时优于VSC算法。
(3)针对有些实际网络系统无法准确获得流体模型的问题,提出了基于自适应单神经元变结构控制的AQM算法ANVSC,它由切换控制和采用纠错学习算法的单神经元等价控制组成,不需要流体的精确数学模型就可以保证滑模面状态可达并具有较小的抖振,对负载数量和回路延时等不确定性具有很强的自适应性。仿真表明该算法在动静态的单瓶颈、多瓶颈链路和混合流的网络情景下都表现出很好的稳定性和鲁棒性。
With the increasing level of information, Internet technology has been closely interrelated to people's lives. On the one hand the number of Internet users experience explosive growth, on the other hand many new services such as voice, video, and other multimedia streams appeared for the passed few years. But the growth of data traffic causes a great burden to the routing node. As a result, the Internet quality of service has been badly influenced, which result in more serious network congestion.
AQM algorithm is the best way to solve the network congestion problem, this paper proposes several AQM algorithms focused on the stability and robustness of network. The contributions of this thesis are as follows:
(1) Because of many uncertain factors in the network, an AQM algorithm based on variable structure control is proposed. VSC algorithm which is simply designed, easy to realize, not depended on the object model has strong robustness to those uncertain factors, and be good at nonlinear control. The simulation results show that the algorithm has better stability, small network latency, and robustness to the changes of the network.
(2) In order to weaken the jitter of the VSC controller, this paper proposes two new AQM algorithms based on intelligent VSC. FVSC and NVSC algorithm which take advantage of fuzzy reasoning and the gradient learning of the single neuron adjust the controller parameter. They inherit the merits of the VSC algorithm and also reduce the jitter. Simulation results show that these two algorithms not only retain the good performance of the VSC algorithm, but also keep better queue length in the same network environment.
(3) Because the network cannot build precise mathematic model, an AQM algorithm based on adaptive single neuron and variable structure control is proposed for the situation. The corrected control is designed to make the state vector arrive the sliding surface and weaken the jitter, and the equivalent control which outputs from the single neuron is adaptive to the uncertainties. Simulation results prove that the ANVSC algorithm show good stability and robustness in different network environment.
AQM算法是目前解决拥塞问题的有效方法,本文在已有AQM算法的基础上,提出了稳定性与鲁棒性强的几种队列管理算法,所做的主要工作如下：
(1)针对网络中存在负载数量和回路延时等不确定因素,提出了基于变结构控制的AQM算法,其中作为拥塞指示的切换函数是队列长度误差和输入速率与链路容量之差的线性组合,拥塞控制策略设计简单,易于实现,不依赖被控对象的模型,很好地解决了网络拥塞控制问题。用NS2网络仿真软件验证了VSC算法的性能,它不仅具有良好的队列稳定性和较小的队列延时,同时对网络环境的变化具有很强的鲁棒性。
(2)针对变结构控制中存在的抖振问题,提出了两种基于智能变结构的AQM算法FVSC、NVSC,其中FVSC算法和NVSC算法根据拥塞的状况,分别采用模糊推理算法和单神经元梯度学习算法,自适应调节控制器中的参数,它们继承了VSC算法鲁棒性强的优点同时减弱了VSC算法的抖振。仿真实验表明FVSC算法与NVSC算法保留了VSC算法的良好性能,并且在相同网络环境下队列稳定性、队列延时优于VSC算法。
(3)针对有些实际网络系统无法准确获得流体模型的问题,提出了基于自适应单神经元变结构控制的AQM算法ANVSC,它由切换控制和采用纠错学习算法的单神经元等价控制组成,不需要流体的精确数学模型就可以保证滑模面状态可达并具有较小的抖振,对负载数量和回路延时等不确定性具有很强的自适应性。仿真表明该算法在动静态的单瓶颈、多瓶颈链路和混合流的网络情景下都表现出很好的稳定性和鲁棒性。
With the increasing level of information, Internet technology has been closely interrelated to people's lives. On the one hand the number of Internet users experience explosive growth, on the other hand many new services such as voice, video, and other multimedia streams appeared for the passed few years. But the growth of data traffic causes a great burden to the routing node. As a result, the Internet quality of service has been badly influenced, which result in more serious network congestion.
AQM algorithm is the best way to solve the network congestion problem, this paper proposes several AQM algorithms focused on the stability and robustness of network. The contributions of this thesis are as follows:
(1) Because of many uncertain factors in the network, an AQM algorithm based on variable structure control is proposed. VSC algorithm which is simply designed, easy to realize, not depended on the object model has strong robustness to those uncertain factors, and be good at nonlinear control. The simulation results show that the algorithm has better stability, small network latency, and robustness to the changes of the network.
(2) In order to weaken the jitter of the VSC controller, this paper proposes two new AQM algorithms based on intelligent VSC. FVSC and NVSC algorithm which take advantage of fuzzy reasoning and the gradient learning of the single neuron adjust the controller parameter. They inherit the merits of the VSC algorithm and also reduce the jitter. Simulation results show that these two algorithms not only retain the good performance of the VSC algorithm, but also keep better queue length in the same network environment.
(3) Because the network cannot build precise mathematic model, an AQM algorithm based on adaptive single neuron and variable structure control is proposed for the situation. The corrected control is designed to make the state vector arrive the sliding surface and weaken the jitter, and the equivalent control which outputs from the single neuron is adaptive to the uncertainties. Simulation results prove that the ANVSC algorithm show good stability and robustness in different network environment.
引文
[1]胡道远.面向21世纪计算机网络的发展[J].世界网络与多媒体,1999,7(12)：12～14.
[2]Nagle J. Congestion control in TCP/IP Internetwork[J]. IETF RFC896,1984.
[3]Tran G, Phuoc. Trends towards Next Generation Internet[C]. Conference on Next Generation Internet Networks,3rd Euro NGL,2007,5:xvi～xvii.
[4]Jain R, Ramakrishnan K K, Chiu Dah-Ming. Congestion avoidance in computer networks with a connectionless network layer[R]. Technical Report, DEC-TR-506, Digital Equipment Corporation,1988.
[5]Tanenbaum A S. Computer Networks 3rd ed[J]. Prentice Hall, Inc,1996.
[6]罗万明,林闯,闫保平.TCP／IP拥塞控制研究[J].计算机学报,2001,24(1)：1～18.
[7]Postel J. Transmission Control Protocol[J]. RFC 793,1981.
[8]Peterson L L, Davie B S. Computer Networks:a System Approach[J]. Morgan Kaufmann Publishers,2000.
[9]Jacobson V. Congestion avoidance and control[J]. ACM Computer Communication Review,1988,18(4):314～329.
[10]Stevens W. TCP Slow Start, Congestion Avoidance, Fast Retransmit, and Fast Recovery Algorithms[C]. RFC 2001,1997.
[11]Floyd, Henderson T. The New Reno Modification to TCP's Fast Recovery Algorithm[C]. RFC 2582,1999.
[12]Clark D, hoe J. Start-up Dynamics of TCP's congestion control and avoidance schemes[R]. Technical report, Jun.1995, Presentation to Internet End-to-End Research Group.
[13]Lawrence S, Brak M, and Larry L. TCP Vegas:End to end congestion avoidance on a global internet[J]. IEEE Journal on Selected Areas in Communications, Oct. 1995.13(8):pp1465～1480.
[14]Brakino L S. TCP-vegas:new techniques for congestion detection & avoidance[J]. In: Proc of SIGGCOMM'99, Sep 1994.
[15]任丰原,林闯,刘卫东.IP网络中的拥塞控制[J].计算机学报,2003,26(9)：1025～1034.
[16]Braden B, Clark D, Crowcroft J. Recommendations on Queue Management and Congestion A voidance in the Internet [J]. RFC2 309,1994.
[17]S Floyd, V Jacobson. Random early detection gateway for congestion avoidance[J]. IEEE/ACM Transactions on Network,1993,1(4):397～413.
[18]Feng W, Kandlur D, Saha D. A self-configuring RED gateway[J]. Proceedings of the IEEE INFOCOM. New York:IEEE Communications Society,1999.1320～1328.
[19]S Floyd, R Gummadi, S Shenker. Adaptive RED:An algorithm for increasing the robustness of RED [J].2001.
[20]T J Ott, T V Lakshman, L H Wong. SRED:Stabilized RED[J]. Proceeding of IEEE INFOCOM, Amsterdam:Elsevier Press,1999,1346～1355.
[21]Anjum F, Tassiulas L. Balance-RED:An algorithm to achieve fairness in Internet[J]. In: Proceeding of IEEE INFOCOM1999, New York, USA,1999.
[22]James Aweya, Michel Ouellette, Delfin Y, Montuno. DRED:a random early detection algorithm for TCP/IP networks[J]. International Journal of Communication Systems, 2002,15(1):287～307.
[23]Songtao Guo, Xiaofeng Liao, Chuandong Li, Degang Yang. Stability analysis of a novel exponential-RED model with heterogeneous delays[J]. In Proc:Computer Communicati-ons[J]. Mar,2007,30(5):1058～1074.
[24]Lin D, Morris R. Dynamics of Random Early Detection[J]. Computer Communication Review, Oct.1997,27(4):127～137.
[25]Chonggang Wang, Jiangchuan Liu, Bo Li, Kazem Sohraby. LRED:A Robust and Responsive AQM Algorithm Using Packet Loss Ratio Measurement[J]. IEEE Transactions on Parallel and Distributed Systems, Jan.2007,18(1):29～43.
[26]Naixue Xiong, Yan Yang, Xavier Defago Yanxiang He. LRC-RED:A Self-tuning Robust and Adaptive AQM Scheme Internet Congestion[C]. Sixth International Conference on Volume, Issue,05-08 Dec.2005:655～659.
[27]Kaiyu Zhou, Yeung K L, Li V, O K. Nonlinear RED:A simple yet efficient active queue management scheme[J]. Computer Networks, Dec.2006,50(18):3784～3794.
[28]邓晓衡,陈志刚,王建新,曾志文.NARED：一种非线性自适应RED拥塞控制机制[J].2005,26(6)：892～895.
[29]Cisco Company. Distributed weighted random early detection. http://cco.cisco.com.
[30]Wu-chang Feng, D Kandlur, D Saha, K Shin.The blue active queue management algorithms[C]. IEEE/ACM Transactions on Networking, Aug.2002,10(4):513～528.
[31]Srisankar S. Kunniyur, R Srikant. An Adaptive Virtual Queue (AVQ) Algorithm for Active Queue Management[J]. IEEE/ACM Transactions on Networking, April.2004, 12(2):286～299.
[32]Athuraliya S, Steven H, Low, et al. REM:Active Queue Management[J]. IEEE Network Magazine, June.2001,15(3):48-53.
[33]Tan. L, Peng G, Chan S. Adaptive REM:random exponential marking with improved robustness[J]. Electronics Letters, Jan.2007,43(2):133～135.
[34]Yang C, Reddy A. Taxonomy for Congestion Control Algorithms in Packet Switching Networks[J]. IEEE Network Magazine,1995,9:34～45.
[35]Misra V, Gong W, Towsley D. Fluid-based Analysis of a Network of AQM Routers Supporting TCP Flows[J]. In:Proceeding ACM/SIGCOMM 2000, Sweden,2000, 151～160.
[36]Hollot C V, Misra V, Towsley D, Gong W. On Designing Improved Controllers For AQM Routers Supporting TCP Flows[J]. In Proc IEEE INFOCOM 2001,3:1726～1734.
[37]S Jinsheng, C Guanrong, K King-Tim, S Chan, M.Zukerman. PD-controller:A New Active Queue Management Scheme[J]. In:Proceedings of IEEE GLOBECOM'03, Dec. 2003,6:3103～3107.
[38]FAN Yanfei, REN Fengyuan, LIN Chuang. Design a PID Controller for Active Queue Management J]. Proceedings of the Eighth IEEE International Symposium on Computers and Communication (ISCC'03).
[39]林闯,单志光,任丰原等.计算机网路的服务质量(Qos)[M].北京：清华大学出版社.2004.
[40]Y Du, N Wang. A PID controller with neuron tuning parameters for multi-model plants[C]. Proceedings of 2004 International Conference on Machine Learning and Cybernetics,2004,6:3408～3411.
[41]B Hariri, N Sadati. NN-RED:An AQM mechanism based on neural networks[J]. Proceedings of Electronics Letters,2007,43(19).
[42]苏聪,陈元琰,罗晓曙,吴东.FBLUE：基于模糊理论的主动队列管理算法[J],计算机工程与应用,2006.
[43]蔡小玲,汪小帆,王执铨.主动队列管理中PI控制的分析与改进[J].南京理工大学学报,2005,29(3)：368～370.
[44]W Jun song, G Zhi wei, S Yan tai. RBF-PID based adaptive active queue management algorithm for TCP network[C]. Proceedings of 2007 IEEE International Conference on Control and Automation,2007:171～176.
[45]陆锦军,王执铨.基于一类新PID的网络拥塞控制算法[J],上海交通大学学报,2008,32(2)：218-221.
[46]C Chang Kuo, K Hang Hong, Y Jun Juh. GA-based PID active queue management control design for a class of TCP communication networks[J]. Proceedings of 2008 Elsevier,2008.
[47]Jain R, Chiu D M. Quantitative measure of fairness and discrimination for resource allocation in shared systems[C]. DEC. TR-301, Littleton, MA:Digital equipment corporation.
[48]Seddigh N, Nandy B, Pieda P. Bandwidth Assurance Issues for TCP Flows in a Differentiated Service Network[J]. IEEE GLOBECOM'99, Dec.1999,3:1792～1798.
[49]Pan R, Prabhakar B, Psounis K. CHOKe:A Stateless Active Queue Management Scheme For Approximating Fair Bandwidth Allocation[J]. in Proc. IEEE INFOCOM 2000,2 942～951.
[50]Wu-Chang Feng, Kandlur D D, Saha D, Shin K G. Stochastic fair blue:A queue management algorithm for enforcing fairness[C]. IEEE INFOCOM 2001. Conference on Computer Communications,2001,3:1520～1529.
[51]Chatanon G, Labrador M, Banerjee S. BLACK:Detection and Preferential Dropping of High Bandwidth Unresponsive Flows[J]. IEEE International Conference on commun-ication 2003,1:664～668.
[52]Jung-Shian Li, Ming-Shiann Leu. Fair Bandwidth Share Using Flow Number Estimate[J]. IEEE International Conference on Communications. Conference,2002,2:1274～1278.
[53]Stoica I, Shenker S, Zhang H. Core-Stateless Fair Queuing:Achieving Approximately Fair Bandwidth Allocations in High Speed Networks[J]. Proceedings of ACM SIGCOMM'98,1998:118～130.
[54]王辉.NS2网络模拟器的原理和应用[M].西安：西北工业大学出版社,2008.
[55]Lin JS, Yan JJ, Liao TL. Robust control of chaos in Lorenz systems subject to mismatch uncertainties[J]. Chaos, Solitons Fractals 2006,21:501～10.
[56]Itkis U. Control system of variable structure[J]. New York:Wiley,1976.
[57]高为炳.变结构控制的理论基础[M].北京：中国科学出版社,1990.
[58]Utkin VI. Sliding mode and their applications in variable structure systems[J]. Moscow: Mir Editors,1978.
[59]Jacbson V, Karels M. Congestion avoidance and control[J]. In Proceeding of ACM SIGCOMM'88. CA, California,1988.
[60]Sun J, Zukerman M. An Adaptive Neuron AQM for Stable Internet[J]. IFIP International Federation for Information Processing,2007:844～854.
[61]R G, Morgan, U Ozguner, A decentralized variable structure control algorithm for robotic manipulators[J]. IEEE J Robot Automat,1985:57～65.
[62]John Y, Hung, James C. Chattering Reduction in Variable Structure Control[J]. Proceeding of IECON'94 IEEE,1994:1914～1918.
[63]高为炳.变结构控制研究的发展与现状[J].控制与决策,1997,8(4)：241～248.
[64]周立芳,钱积新.一种削弱抖动的变结构控制系统设计方法：模糊变结构控制器[J].浙江大学学报,1986：244-248.
[65]陈增强,卢钊,袁著祉.不确定系统的神经网络变结构控制[J].南开大学学报,2001,34(4)：48～53.
[2]Nagle J. Congestion control in TCP/IP Internetwork[J]. IETF RFC896,1984.
[3]Tran G, Phuoc. Trends towards Next Generation Internet[C]. Conference on Next Generation Internet Networks,3rd Euro NGL,2007,5:xvi～xvii.
[4]Jain R, Ramakrishnan K K, Chiu Dah-Ming. Congestion avoidance in computer networks with a connectionless network layer[R]. Technical Report, DEC-TR-506, Digital Equipment Corporation,1988.
[5]Tanenbaum A S. Computer Networks 3rd ed[J]. Prentice Hall, Inc,1996.
[6]罗万明,林闯,闫保平.TCP／IP拥塞控制研究[J].计算机学报,2001,24(1)：1～18.
[7]Postel J. Transmission Control Protocol[J]. RFC 793,1981.
[8]Peterson L L, Davie B S. Computer Networks:a System Approach[J]. Morgan Kaufmann Publishers,2000.
[9]Jacobson V. Congestion avoidance and control[J]. ACM Computer Communication Review,1988,18(4):314～329.
[10]Stevens W. TCP Slow Start, Congestion Avoidance, Fast Retransmit, and Fast Recovery Algorithms[C]. RFC 2001,1997.
[11]Floyd, Henderson T. The New Reno Modification to TCP's Fast Recovery Algorithm[C]. RFC 2582,1999.
[12]Clark D, hoe J. Start-up Dynamics of TCP's congestion control and avoidance schemes[R]. Technical report, Jun.1995, Presentation to Internet End-to-End Research Group.
[13]Lawrence S, Brak M, and Larry L. TCP Vegas:End to end congestion avoidance on a global internet[J]. IEEE Journal on Selected Areas in Communications, Oct. 1995.13(8):pp1465～1480.
[14]Brakino L S. TCP-vegas:new techniques for congestion detection & avoidance[J]. In: Proc of SIGGCOMM'99, Sep 1994.
[15]任丰原,林闯,刘卫东.IP网络中的拥塞控制[J].计算机学报,2003,26(9)：1025～1034.
[16]Braden B, Clark D, Crowcroft J. Recommendations on Queue Management and Congestion A voidance in the Internet [J]. RFC2 309,1994.
[17]S Floyd, V Jacobson. Random early detection gateway for congestion avoidance[J]. IEEE/ACM Transactions on Network,1993,1(4):397～413.
[18]Feng W, Kandlur D, Saha D. A self-configuring RED gateway[J]. Proceedings of the IEEE INFOCOM. New York:IEEE Communications Society,1999.1320～1328.
[19]S Floyd, R Gummadi, S Shenker. Adaptive RED:An algorithm for increasing the robustness of RED [J].2001.
[20]T J Ott, T V Lakshman, L H Wong. SRED:Stabilized RED[J]. Proceeding of IEEE INFOCOM, Amsterdam:Elsevier Press,1999,1346～1355.
[21]Anjum F, Tassiulas L. Balance-RED:An algorithm to achieve fairness in Internet[J]. In: Proceeding of IEEE INFOCOM1999, New York, USA,1999.
[22]James Aweya, Michel Ouellette, Delfin Y, Montuno. DRED:a random early detection algorithm for TCP/IP networks[J]. International Journal of Communication Systems, 2002,15(1):287～307.
[23]Songtao Guo, Xiaofeng Liao, Chuandong Li, Degang Yang. Stability analysis of a novel exponential-RED model with heterogeneous delays[J]. In Proc:Computer Communicati-ons[J]. Mar,2007,30(5):1058～1074.
[24]Lin D, Morris R. Dynamics of Random Early Detection[J]. Computer Communication Review, Oct.1997,27(4):127～137.
[25]Chonggang Wang, Jiangchuan Liu, Bo Li, Kazem Sohraby. LRED:A Robust and Responsive AQM Algorithm Using Packet Loss Ratio Measurement[J]. IEEE Transactions on Parallel and Distributed Systems, Jan.2007,18(1):29～43.
[26]Naixue Xiong, Yan Yang, Xavier Defago Yanxiang He. LRC-RED:A Self-tuning Robust and Adaptive AQM Scheme Internet Congestion[C]. Sixth International Conference on Volume, Issue,05-08 Dec.2005:655～659.
[27]Kaiyu Zhou, Yeung K L, Li V, O K. Nonlinear RED:A simple yet efficient active queue management scheme[J]. Computer Networks, Dec.2006,50(18):3784～3794.
[28]邓晓衡,陈志刚,王建新,曾志文.NARED：一种非线性自适应RED拥塞控制机制[J].2005,26(6)：892～895.
[29]Cisco Company. Distributed weighted random early detection. http://cco.cisco.com.
[30]Wu-chang Feng, D Kandlur, D Saha, K Shin.The blue active queue management algorithms[C]. IEEE/ACM Transactions on Networking, Aug.2002,10(4):513～528.
[31]Srisankar S. Kunniyur, R Srikant. An Adaptive Virtual Queue (AVQ) Algorithm for Active Queue Management[J]. IEEE/ACM Transactions on Networking, April.2004, 12(2):286～299.
[32]Athuraliya S, Steven H, Low, et al. REM:Active Queue Management[J]. IEEE Network Magazine, June.2001,15(3):48-53.
[33]Tan. L, Peng G, Chan S. Adaptive REM:random exponential marking with improved robustness[J]. Electronics Letters, Jan.2007,43(2):133～135.
[34]Yang C, Reddy A. Taxonomy for Congestion Control Algorithms in Packet Switching Networks[J]. IEEE Network Magazine,1995,9:34～45.
[35]Misra V, Gong W, Towsley D. Fluid-based Analysis of a Network of AQM Routers Supporting TCP Flows[J]. In:Proceeding ACM/SIGCOMM 2000, Sweden,2000, 151～160.
[36]Hollot C V, Misra V, Towsley D, Gong W. On Designing Improved Controllers For AQM Routers Supporting TCP Flows[J]. In Proc IEEE INFOCOM 2001,3:1726～1734.
[37]S Jinsheng, C Guanrong, K King-Tim, S Chan, M.Zukerman. PD-controller:A New Active Queue Management Scheme[J]. In:Proceedings of IEEE GLOBECOM'03, Dec. 2003,6:3103～3107.
[38]FAN Yanfei, REN Fengyuan, LIN Chuang. Design a PID Controller for Active Queue Management J]. Proceedings of the Eighth IEEE International Symposium on Computers and Communication (ISCC'03).
[39]林闯,单志光,任丰原等.计算机网路的服务质量(Qos)[M].北京：清华大学出版社.2004.
[40]Y Du, N Wang. A PID controller with neuron tuning parameters for multi-model plants[C]. Proceedings of 2004 International Conference on Machine Learning and Cybernetics,2004,6:3408～3411.
[41]B Hariri, N Sadati. NN-RED:An AQM mechanism based on neural networks[J]. Proceedings of Electronics Letters,2007,43(19).
[42]苏聪,陈元琰,罗晓曙,吴东.FBLUE：基于模糊理论的主动队列管理算法[J],计算机工程与应用,2006.
[43]蔡小玲,汪小帆,王执铨.主动队列管理中PI控制的分析与改进[J].南京理工大学学报,2005,29(3)：368～370.
[44]W Jun song, G Zhi wei, S Yan tai. RBF-PID based adaptive active queue management algorithm for TCP network[C]. Proceedings of 2007 IEEE International Conference on Control and Automation,2007:171～176.
[45]陆锦军,王执铨.基于一类新PID的网络拥塞控制算法[J],上海交通大学学报,2008,32(2)：218-221.
[46]C Chang Kuo, K Hang Hong, Y Jun Juh. GA-based PID active queue management control design for a class of TCP communication networks[J]. Proceedings of 2008 Elsevier,2008.
[47]Jain R, Chiu D M. Quantitative measure of fairness and discrimination for resource allocation in shared systems[C]. DEC. TR-301, Littleton, MA:Digital equipment corporation.
[48]Seddigh N, Nandy B, Pieda P. Bandwidth Assurance Issues for TCP Flows in a Differentiated Service Network[J]. IEEE GLOBECOM'99, Dec.1999,3:1792～1798.
[49]Pan R, Prabhakar B, Psounis K. CHOKe:A Stateless Active Queue Management Scheme For Approximating Fair Bandwidth Allocation[J]. in Proc. IEEE INFOCOM 2000,2 942～951.
[50]Wu-Chang Feng, Kandlur D D, Saha D, Shin K G. Stochastic fair blue:A queue management algorithm for enforcing fairness[C]. IEEE INFOCOM 2001. Conference on Computer Communications,2001,3:1520～1529.
[51]Chatanon G, Labrador M, Banerjee S. BLACK:Detection and Preferential Dropping of High Bandwidth Unresponsive Flows[J]. IEEE International Conference on commun-ication 2003,1:664～668.
[52]Jung-Shian Li, Ming-Shiann Leu. Fair Bandwidth Share Using Flow Number Estimate[J]. IEEE International Conference on Communications. Conference,2002,2:1274～1278.
[53]Stoica I, Shenker S, Zhang H. Core-Stateless Fair Queuing:Achieving Approximately Fair Bandwidth Allocations in High Speed Networks[J]. Proceedings of ACM SIGCOMM'98,1998:118～130.
[54]王辉.NS2网络模拟器的原理和应用[M].西安：西北工业大学出版社,2008.
[55]Lin JS, Yan JJ, Liao TL. Robust control of chaos in Lorenz systems subject to mismatch uncertainties[J]. Chaos, Solitons Fractals 2006,21:501～10.
[56]Itkis U. Control system of variable structure[J]. New York:Wiley,1976.
[57]高为炳.变结构控制的理论基础[M].北京：中国科学出版社,1990.
[58]Utkin VI. Sliding mode and their applications in variable structure systems[J]. Moscow: Mir Editors,1978.
[59]Jacbson V, Karels M. Congestion avoidance and control[J]. In Proceeding of ACM SIGCOMM'88. CA, California,1988.
[60]Sun J, Zukerman M. An Adaptive Neuron AQM for Stable Internet[J]. IFIP International Federation for Information Processing,2007:844～854.
[61]R G, Morgan, U Ozguner, A decentralized variable structure control algorithm for robotic manipulators[J]. IEEE J Robot Automat,1985:57～65.
[62]John Y, Hung, James C. Chattering Reduction in Variable Structure Control[J]. Proceeding of IECON'94 IEEE,1994:1914～1918.
[63]高为炳.变结构控制研究的发展与现状[J].控制与决策,1997,8(4)：241～248.
[64]周立芳,钱积新.一种削弱抖动的变结构控制系统设计方法：模糊变结构控制器[J].浙江大学学报,1986：244-248.
[65]陈增强,卢钊,袁著祉.不确定系统的神经网络变结构控制[J].南开大学学报,2001,34(4)：48～53.