认知网络中具有自主学习特征的智能QoS保障机制研究
|
摘要
认知行为模型首先检测网络当前的状态,然后根据观察到的网络条件和参数进行调整、判决、执行。认知技术使得通信实体具有认知周围环境的能力,并能根据周围环境的变化智能、自主、自适应地动态变化。将认知的概念和功能引入现有的信息网络就构成了认知网络。然而,以端到端QoS (Quality of Service)性能最优化为目标的认知网络的研究在国内外还都处于萌芽阶段,仅有一个大致的网络概念模型和少量认知路由算法。认知网络中QoS机制的实现,即资源预约、资源调度和管理等问题至今还缺乏可行的解决方案。因此,本文将基于网络行为模型,研究认知网络的QoS保障机制,本文是国家高技术研究发展计划(863计划)课题的一部分。
本文主要提出了三个算法和机制,包括基于蚁群算法的多径路由并行传输协议、预留资源的自适应借用策略、以及基于神经网络的混合网络流量预测模型。详细内容如下。
(1)在认知网络中支持流媒体传输的多径路由算法方面,本文通过改进蚁群算法,提出能够规避和快速缓解拥塞的多径路由协议命名为AMP算法。AMP算法在源节点和目的节点之间寻找多条独立的可用路径,并构成有效传输路径集。根据每条路径上的带宽资源和网络负载情况,对集合中的路径进行优先级排队,确定多条传输路径并行传输,改善流媒体业务的服务质量。当主路由发生拥塞时,迅速使用路径集中的备用录用替换原有路由,保证传输的连续性。同时,启动新的路径搜索算法,即在目的节点和源节点同时发送寻路蚂蚁,双方向发现新路由,能够更加迅速的发现新路径,规避拥塞。另外,AMP算法使用改进了的蚂蚁寻路准则,使得该算法可以实现多QoS约束的最优路由,即同时满足时延和带宽约束的路由。
(2)在预留资源的自适应借用与吞吐量优化方面,本文引入自适应借用的思想,提出了预留资源的借用策略,命名为RBFR策略。在传统的信息网络中,预留资源在有效期内具有独占性和专用性,而数据业务的突发特点使发送端输出的数据流不连贯,造成相应的预留资源不定期的处于闲置状态,导致资源浪费。在网络负载较重的情况下,占整体资源比例较大的预留资源有部分闲置,而网络中剩余的可用资源无法满足更多应用的接入需求,限制了吞吐量的提高。因此,充分利用认知网络的自学习和重配置功能,实现预留资源的自适应借用,是提高网络吞吐量、改进网络性能的重要手段。于是,本文将节点的资源类型分为三类：预留资源、本地资源和额外资源,提出在保证已预留资源的数据流服务质量的前提下,允许实时业务在满足相应规定时借用节点闲置的预留资源,非实时业务不允许借用其他节点的资源。RBFR策略还给出了相应的资源分配和借用规则,并使额外资源在使用完毕后按本文给出的规则归还。RBFR策略不仅保证了实时业务和非实时业务的公平性,而且可以灵活协调多种业务,优化配置网络资源,改善系统整体吞吐量,提高资源利用效率。
(3)在认知网络的流量调度与负载均衡方面,本文将神经网络的预测方法引入认知网络,提出基于神经网络的混合神经网络预测模型,命名为Ant Double-BP模型。该模型利用神经网络的非线性处理和容噪能力,综合考虑终端的分布状况和用户业务的QoS需求,实时跟踪网络状态,预测网络流量。另外,该模型使用蚁群算法训练BP (Back Propagation)神经网络的权值,使得BP网络的权值不依赖于训练样本；并在拟合之前剔除原始数据中的异常数据,这些做法都排除了训练样本对模型精度的影响。同时,使用混合的小波神经网络模型预测网络流量,提高了对非线性、多时间尺度变化的网络流量的预测精度。
The network state is detected by cognitive networks model first, then the cognitive networks could do adjust, judgement and execution based on the conditions it observed. Cognitive network can perceive the external environment; intelligently and automatically change its behavior to adapt to the environment. It is more appropriate to provide security for users with QoS (Quality of Service). The study of cognitive networks for optimizing the end-to-end QoS is in its infancy stage at home and abroad, only a general concept model and a few cognitive routing algorithms. The implementation of QoS mechanisms in the cognitive networks, that is, classification and definition of the QoS parameters, access control and negotiation, resource reservation, resource scheduling and management, is not solved yet. So, in this dissertation, I will study the QoS guarantee mechanisms based on cognitive networks, which is one part of the High Technology Research and Development Program of China (863Plan)(No.2009AA01Z11).
Three algorithms and mechanisms are proposed in this dissertation, including ant-based multiple-path routing algorithm with congestion avoidance, resource borrowing from reservation strategy and a network traffic prediction model based on hybrid neural network.
(1) In order to support multiple-path transmission of streaming media, an ant-based multiple-path routing algorithm with congestion avoidance (AMP) is proposed in this dissertation, through analyzing the present multiple-path routing algorithm and ant algorithm. It adopts double-way ant-exploration methods to speed up the exploration for the optimal routes. The new guide line better satisfies the demands of OoS. Simulation contrast with OPNET shows that the algorithm is valid and effective in controlling the packet loss ratio, delay and the residual bandwidth.
(2) For the adaptive borrowing of reservation resources and throughput optimization, we adopt adaptive borrowing idea in this dissertation and propose a strategy which borrowing resource from idle reservation (RBFR) according to the characteristics and advantages of cognitive networks. The proposed strategy adds function module in nodes. First, it considers the type of new requests, and then assigns resource according to their different parameters. If the available resource can not meet the requirements of the new request, real-time request is accesses of higher priority and borrows the idle reservation from non-real-time business appropriately. Comprehensive simulations show that, RBFR has good performance at packet loss rate, network resource utilization and the rejected rate of new requests.
(3) In order to realize the traffic scheduling and load balancing, a hybrid traffic prediction model (Ant Double-BP model) is proposed in this dissertation, which training BP algorithm with Ant Colony System based on the analysis of the present models. It avoids the problem of slow convergence speed and easily falling into local optimum problem existed in the gradient descent method. Besides, before the prediction, we reject the abnormal data in the recognition network first, and then begin wavelet decomposition, at last we predict the network traffic with the hybrid model, thus the traffic prediction with high-precision in cognitive network will be achieved.
本文主要提出了三个算法和机制,包括基于蚁群算法的多径路由并行传输协议、预留资源的自适应借用策略、以及基于神经网络的混合网络流量预测模型。详细内容如下。
(1)在认知网络中支持流媒体传输的多径路由算法方面,本文通过改进蚁群算法,提出能够规避和快速缓解拥塞的多径路由协议命名为AMP算法。AMP算法在源节点和目的节点之间寻找多条独立的可用路径,并构成有效传输路径集。根据每条路径上的带宽资源和网络负载情况,对集合中的路径进行优先级排队,确定多条传输路径并行传输,改善流媒体业务的服务质量。当主路由发生拥塞时,迅速使用路径集中的备用录用替换原有路由,保证传输的连续性。同时,启动新的路径搜索算法,即在目的节点和源节点同时发送寻路蚂蚁,双方向发现新路由,能够更加迅速的发现新路径,规避拥塞。另外,AMP算法使用改进了的蚂蚁寻路准则,使得该算法可以实现多QoS约束的最优路由,即同时满足时延和带宽约束的路由。
(2)在预留资源的自适应借用与吞吐量优化方面,本文引入自适应借用的思想,提出了预留资源的借用策略,命名为RBFR策略。在传统的信息网络中,预留资源在有效期内具有独占性和专用性,而数据业务的突发特点使发送端输出的数据流不连贯,造成相应的预留资源不定期的处于闲置状态,导致资源浪费。在网络负载较重的情况下,占整体资源比例较大的预留资源有部分闲置,而网络中剩余的可用资源无法满足更多应用的接入需求,限制了吞吐量的提高。因此,充分利用认知网络的自学习和重配置功能,实现预留资源的自适应借用,是提高网络吞吐量、改进网络性能的重要手段。于是,本文将节点的资源类型分为三类：预留资源、本地资源和额外资源,提出在保证已预留资源的数据流服务质量的前提下,允许实时业务在满足相应规定时借用节点闲置的预留资源,非实时业务不允许借用其他节点的资源。RBFR策略还给出了相应的资源分配和借用规则,并使额外资源在使用完毕后按本文给出的规则归还。RBFR策略不仅保证了实时业务和非实时业务的公平性,而且可以灵活协调多种业务,优化配置网络资源,改善系统整体吞吐量,提高资源利用效率。
(3)在认知网络的流量调度与负载均衡方面,本文将神经网络的预测方法引入认知网络,提出基于神经网络的混合神经网络预测模型,命名为Ant Double-BP模型。该模型利用神经网络的非线性处理和容噪能力,综合考虑终端的分布状况和用户业务的QoS需求,实时跟踪网络状态,预测网络流量。另外,该模型使用蚁群算法训练BP (Back Propagation)神经网络的权值,使得BP网络的权值不依赖于训练样本；并在拟合之前剔除原始数据中的异常数据,这些做法都排除了训练样本对模型精度的影响。同时,使用混合的小波神经网络模型预测网络流量,提高了对非线性、多时间尺度变化的网络流量的预测精度。
The network state is detected by cognitive networks model first, then the cognitive networks could do adjust, judgement and execution based on the conditions it observed. Cognitive network can perceive the external environment; intelligently and automatically change its behavior to adapt to the environment. It is more appropriate to provide security for users with QoS (Quality of Service). The study of cognitive networks for optimizing the end-to-end QoS is in its infancy stage at home and abroad, only a general concept model and a few cognitive routing algorithms. The implementation of QoS mechanisms in the cognitive networks, that is, classification and definition of the QoS parameters, access control and negotiation, resource reservation, resource scheduling and management, is not solved yet. So, in this dissertation, I will study the QoS guarantee mechanisms based on cognitive networks, which is one part of the High Technology Research and Development Program of China (863Plan)(No.2009AA01Z11).
Three algorithms and mechanisms are proposed in this dissertation, including ant-based multiple-path routing algorithm with congestion avoidance, resource borrowing from reservation strategy and a network traffic prediction model based on hybrid neural network.
(1) In order to support multiple-path transmission of streaming media, an ant-based multiple-path routing algorithm with congestion avoidance (AMP) is proposed in this dissertation, through analyzing the present multiple-path routing algorithm and ant algorithm. It adopts double-way ant-exploration methods to speed up the exploration for the optimal routes. The new guide line better satisfies the demands of OoS. Simulation contrast with OPNET shows that the algorithm is valid and effective in controlling the packet loss ratio, delay and the residual bandwidth.
(2) For the adaptive borrowing of reservation resources and throughput optimization, we adopt adaptive borrowing idea in this dissertation and propose a strategy which borrowing resource from idle reservation (RBFR) according to the characteristics and advantages of cognitive networks. The proposed strategy adds function module in nodes. First, it considers the type of new requests, and then assigns resource according to their different parameters. If the available resource can not meet the requirements of the new request, real-time request is accesses of higher priority and borrows the idle reservation from non-real-time business appropriately. Comprehensive simulations show that, RBFR has good performance at packet loss rate, network resource utilization and the rejected rate of new requests.
(3) In order to realize the traffic scheduling and load balancing, a hybrid traffic prediction model (Ant Double-BP model) is proposed in this dissertation, which training BP algorithm with Ant Colony System based on the analysis of the present models. It avoids the problem of slow convergence speed and easily falling into local optimum problem existed in the gradient descent method. Besides, before the prediction, we reject the abnormal data in the recognition network first, and then begin wavelet decomposition, at last we predict the network traffic with the hybrid model, thus the traffic prediction with high-precision in cognitive network will be achieved.
引文
[1]Carolina Fortuna, Mihael. Trends in the development of communication networks:cognitive networks. Computer Networks.2009,53(9):1354-1376.
[2]R.W. Thomas. Cognitive networks. Ph.D. dissertation. Virginia Polytechnic and State University, Blacksburg, VA,2007,58-60.
[3]Q. Mahmoud, Cognitive networks-towards self-aware networks. John Wiley and Sons,2007, ISBN 9780470061961.
[4]Clark David D., Partridge Craig, Christopher Ramming J., Wroclawski John T.. A knowledge plane for the internet. Proceedings of ACM SIGCOMM 2003 Conference on Computer Communications, Karlsruhe, Germany.2003. Association for Computing Machinery. Germany. Vol.33, No.4, pp.3-10.
[5]Thomas R, Friend D, Dasilva L. Cognitive networks:adaptation and learning to achieve end-to-end performance objectives. IEEE Communication Magazine.2006,44(12):51-57.
[6]Joseph Mitola III. Cognitive radio for flexible mobile multimedia communications. Mobile Networks and Applications.2001,6(5):435-441.
[7]Gelenbe E., Zhiguang Xu, Seref E.. Cognitive packet networks. Tools with Artificial Intelligence. Proceedings:11th IEEE International Conference on,1999, Chicago, IL, USA. IEEE Piscataway, NJ, United States.1999, pp.47-54.
[8]Thomas R.W., DaSilva L.A., Mackenzie A.B.. Cognitive networks. IEEE New Frontiers in Dynamic Spectrum Access Networks, DySPAN,8-11 Nov.2005:352-360.
[9]M. A. L. Thathachar, P. S. Sastry. Networks of Learning Automata, Kluwer,2004.
[10]Ryan W. Thomas, Daniel H. Friend, Luiz A. Dasilva, Allen B. Mackenzie. Cognitive networks:adaptation and learning to achieve end-to-end performance objectives. Communications Magazine IEEE.2006,44(12):51-57.
[11]Mitola J. III. Software Radios:Wireless architectures for the 21st century. Fairfax, VA: Statisfaction,1999.
[12]冯光升,王慧强,马春光,李冰洋,赵倩.面向认知网络的用户QoS动态自配置方法.通信学报,2010,31(3)：133-140.
[13]陈铮,张勇,滕颖蕾,罗希.认知网络概述.无线通信技术,2009,4：21-25,29
[14]Ron Banner and Ariel Orda. Muttipath routing algorithms for congestion minimization. IEEE/ACM Transactions on Networking, Vol.15, No.2,2007, pp.413-424.
[15]李红艳,李建东,周丹.认知网络路由技术.中兴通讯技术,2010,16(1)：50-52.
[16]Perkins CE, Bhagwat P. Highly dynamic destination sequence distance vector (DSDV) routing for mobile computers, In:Proceedings of the ACM SIGCOMM, London, UK,1994.
[17]Broch J, Johnson DB, Maltz DA. The dynamic source routing protocol for mobile ad hoc networks. IETF Internet-draft,1998.
[18]Perkins CE. Ad hoc on-demand distance vector (AODV) routing. IETF Internet-draft,1997.
[19]Anurag K, Manjunath D, Kuri J. Communication networking:an analytical approach. Los Altos, CA:Morgan Kaufmann Publishers,2004. pp.715-716.
[20]Bertsekas D, Gallager R. Data networks,2nd ed. Englewood Cliffs, NJ:Prentice-Hall,1992, pp.162-169.
[21]Pham PP, Perrau S. Performance analysis of reactive shortest path and multipath routing mechanism with load balance. In:Proceedings of the IEEE INFOCOM.2003, San Francisco, California, USA. July 2003, pp.251-259.
[22]Tsirigos A, Haas ZJ, Tabrizi SS. Multipath routing in mobile ad hoc networks or how to route in the presence of frequent topology changes. In:Proceedings of the military communications conference, McLean, VA, United states,2001, Institute of Electrical and Electronics Engineers Inc., October 2001, vol.2, pp.878-883.
[23]John Moy. RFC 2328. OSPF Version 2, IETF,1998.
[24]Jing F, Bhuvaneswaran RS, Katayama Y, Takahashi N. A multipath on-demand routing with path selection probabilities for mobile ad hoc networks. In:Proceedings of the international conference on wireless communications, networking and mobile computing. Wuhan, China. USA. Institute of Electrical and Electronics Engineers Computer Society.2005, vol.2, pp. 1099-1102.
[25]Ye Z, Krishnamurthy SV, Tripathi SK. A framework for reliable routing in mobile ad hoc networks. In:Proceedings of the 22nd annual joint conference of the IEEE computer and communications societies (INFOCOM).2003, San Francisco, CA, United states. Institute of Electrical and Electronics Engineers Inc..2003, vol.1, pp.270-280.
[26]Huang X, Fang Y. End-to-end delay differentiation by prioritized multipath routing in wireless sensor networks. In:Military communications conference. Atlatnic City, NJ, United states. USA. Institute of Electrical and Electronics Engineers Inc..2005, vol.2, pp. 1277-1283.
[27]Popa L, Raiciu C, Stoica I, Rosenblum DS. Reducing congestion effects in wireless networks by multipath routing. In:Proceeding of the 14th IEEE international conference on network protocols. Santa Barbara, California, USA.2006. United states. IEEE Computer Society.2006, pp.96-104.
[28]Li X, Cuthbert L. Stable node-disjoint multipath routing with low overhead in mobile ad hoc networks. In:Proceedings of the IEEE computer society's 12th annual international symposium on modeling, analysis, and simulation of computer and telecommunications systems (MASCOTS 2004). Volendam, Netherlands.2004, USA. IEEE Computer Society. 2004, pp.184-191.
[29]Lou W. An efficient N-to-1 multipath routing protocol in wireless sensor networks. In: Proceedings of the IEEE international conference on mobile ad hoc and sensor systems conference. Washington, DC.2005. USA. Institute of Electrical and Electronics Engineers Computer Society.2005, pp.665-672.
[30]Mao S, Lin S, Wang Y, Panwar SS, Li Y. Multipath video transport over ad hoc networks. IEEE Wireless Communication.2005,12(4):42-49.
[31]Nasipuri A, Das SR. On-demand multipath routing for mobile ad hoc networks. In: Proceedings of the 8th international conference on computer communications and networks, Boston, MA, USA.1999, USA, Institute of Electrical and Electronics Engineers Inc., Oct. 1999. pp.64-70.
[32]Lee S.J., Gerla M.. Split multipath routing with maximally disjoint paths in ad hoc networks. Communications. IEEE International Conference on, Helsinki, Finland.2001, USA. Institute of Electrical and Electronics Engineers Inc.. vol.10, pp.3201-3205.
[33]Wisitpongphan N, Tonguz OK. Disjoint multipath source routing in ad hoc networks: transport capacity. In:Proceedings of the IEEE 58th vehicular technology conference (VTC), Orlando, FL, United states. October 2003. USA. Institute of Electrical and Electronics Engineers Inc..2003. vol.4, pp.2207-2211.
[34]Panichpapiboon S, Ferrai G, Wisitpongphan N, Tonguz OK. Route reservation in ad hoc networks:Is it a good idea. In:Proceedings of the IEEE wireless communication and networking conference (WCNC), Orleans, LA.2005. USA. Institute of Electrical and Electronics Engineers Inc..2005. vol.4, pp.2045-2050.
[35]Dulman S, Wu J, Havinga P. An energy efficient multipath routing algorithm for wireless sensor networks. In:Proceedings of the 6th international symposium on autonomous decentralized systems with an emphasis on advanced distributed transportation systems, Pisa, Italy.2010. USA, IEEE Computer Society.2010, pp.251-256.
[36]Liang Y, Midkiff SF. Multipath Fresnel zone routing for wireless ad hoc networks. In: Proceedings of the IEEE wireless communications and networking conference, New Orleans, LA, United states.2005. USA. Institute of Electrical and Electronics Engineers Inc.. 2005. vol.4, pp.1958-1963.
[37]Ganesan D, Govindan R, Shenker S, Estrin D. Highly-resilient, energy-efficient multipath routing in wireless sensor networks. ACM SIGMOBILE Mobile Computing and Communications Review.2001,5(4):11-25.
[38]舒炎泰,高德云,王雷.无线ad hoc网络中的多径源路由.电子学报,2002,30(2)：279-282.
[39]Wei W, Zakhor A. Robust multipath source routing protocol (RMPSR) for video communication over wireless ad hoc networks. In:IEEE international conference on multimedia and expo, Taipei, Taiwan.2004. USA. Institute of Electrical and Electronics Engineers Inc.2004, vol.2, pp.1379-1382.
[40]Yao Z, Jiang J, Fan P, Cao Z, Li VOK. A neighbor table based multipath routing in ad hoc networks. In:57th IEEE semiannual vehicular technology conference, Jeju, Republic of Korea.2003. USA, Institute of Electrical and Electronics Engineers Inc..2003, vol.3, pp. 1739-1743.
[41]Patrick McCarthy. Dan Grigoras. Multipath associativity based routing. In:Proceedings of the second annual conference on wireless on-demand network systems and services (WONS), St. Moritz, Switzerland, USA, IEEE Computer Society.2005. pp.60-69.
[42]Islam Beltagy, Moustafa Youssef, Mohamed El-Derini. A new routing metric and protocol for multipath routing in cognitive networks. Metric,2011 March,974-979.
[43]Richard E. Tuggle. Cognitive multipath routing for mission critical multi-hop wireless networks.42nd South Eastern Symposium on System Theory University of Texas at Tyler Tyler, TX, USA, March 7-9,2010. Pp.66-71
[44]Suyang Ju, Josehp B Evans. Cognitive multipath multi-channel routing protocol for mobile ad-hoc networks.2010 IEEE Global Telecommunications Conference, GLOBECOM 2010. December 2010. Miami, FL, United states, Pp.1-6.
[45]Dave Clark, Scott Shenker, Lixia Zhang, Deborah Estrin, Sugih Jamin, John Wroclawski, Shai Herzog, Bob Braden. Integrated services in the Internet architecture:An overview. RFC 1633, Jun.1994.
[46]Blake S, Black D, Carlson M, Davies E, Wang Z, Weiss W. An architecture for differentiated services. IETF RFC 2475,1998.
[47]R. Braden Ed., L. Zhang, S. Berson, S. Herzog, S. Jamin. ResourceReser Vation Protocol-Versionl Functional Specification. RFC2205, September 1997.
[48]Long Keping, Cheng Shiduan, Ma Jian. Internet QoS:architectures, Strategies and Mechanisms. High Technology Letters,2001,7(1):13-21.
[49]张知皦.移动网络资源预留QoS技术研究.硕士研究生学位论文.国防科学技术大学图书馆,国防科学技术大学,2003年,Pp.2-27.
[50]Mauthe Andreas, Garcia Francisco, Hutchison David, Yeadon Nicholas. QoS filtering and resource reservation in an internet environment, Multimedia Tools and Applications, vol.13, no.3, March 2001, Pp.285-306.
[51]冯径,承彦,顾冠群.支持适应性路由选择的资源预留协议扩展研究.计算机集成制造系统-CIMS.2002,8(2):155-161.
[52]郭勐,张拥军,彭宇行.一种基于RSVP协议的资源提前保留技术.计算机应用研究.2004,21(2)：238-240.
[53]Terzis A., Krawczyk J., Wroclawski J., Zhang L.. RSVP Operation Over IP Tunnels. RFC 2746, January 2000.
[54]P. Pan, E. Hahne, H. Schulzrinne. BGRP:A tree-based aggregation protocol for inter-domain reservations. Journal of Communication and Networks.2000,2(2):157-167.
[55]R Bless. Towards scalable management of Qos-based end-to-end services. Proc. IEEE Symposium Record on Network Operations and Management Symposium. Seoul, Republic of Korea.2004, USA.Institute of Electrical and Electronics Engineers Inc..2004, Vol.1, pp. 293-306.
[56]Bongkyo Moon, Hamid Aghvami. Quality-of-Service mechanisms in all-IP wireless access networks. IEEE Journal on Selected Areas in Communications.2004,22(5):873-888.
[57]孙毅,张玉成,冯斌,方更法,石晶林,Dutkiewicz Eryk. RSVP协议在移动IPv6网络中的扩展性研究.软件学报,2008,19(7)：1731-1742.
[58]童一飞,李东波.基于资源预测的网格资源预留机制研究.系统仿真学报.2009,21(2)：432-436.
[59]胡春明,怀进鹏,沃天宇.一种基于松弛时间的服务网格资源能力预留机制.计算机研究与发展,2007,44(1)：20-28.
[60]梁泉,杨扬,王元卓.服务网格中基于请求生命期的资源预留方法和策略.控制与决策,2008,23(4)：403-408.
[61]蒲静.基于任务可分的网格资源预留机制,计算机工程与应用,2008,44(12)：118-120,138.
[62]金旗,裴昌幸,朱畅华.ARIMA模型法分析网络流量.西安电子科技大学学报(自然科学版),2003,6(3)：6-10.
[63]Yu Guoqiang, Zhang Changshui. Switching ARIMA model based forecasting for traffic flow. IEEE International Conference on Acoustics, Speech, and Signal Processing. Montreal, Que, Canada.2004, USA, Institute of Electrical and Electronics Engineers Inc..2004, Vol.2, Pp. 429-432.
[64]Sang Aimin, Li Sanqi. A predictability analysis of network traffic. Computer Networks, Elsevier.2002,39(4):329-345.
[65]Gao Chuanshan, Han Liangxiu,Cen Zhiwei, Chu Chunbo. A new multi fractal traffic model based on the wavelet transform. Proceedings of the ISCA 14th International Conference: Parallel and Distributed Computing Systems, Richardson, Texas USA.2001, USA, Association for Computing Machinery.2001. Pp.157-162.
[66]W E Leland, M S Taqqu, W Willinger, D V Wilson. On the self-similar nature of Ethernet traffic (extended version). IEEE/ACM Transactions on Networking,1994,2(1):1-15.
[67]V Paxson, S Floyd. Wide-area traffic:The failure of Poisson modeling. IEEE/ACM Transactions on Networking,1995,3(3):226-244.
[68]Husmeier D, Taylor J G Neural networks for predicting conditional probability densities: improved training scheme combining EM and RVF. Neural Networks,1998,11(1):89,116.
[69]Hussein D. An object-oriented neural network approach to short-term traffic forecasting. European of Operational Research,2001,131(2):253-261.
[70]Wakurah, Zurada JM. Bi-directional computing architecture for time series prediction. Neural Networks,2001,14(9):1307-1321.
[71]De Keyser R M C. et al. A Self-tuning Multi-step. Predictior Application Automatica.1981, 117(1):167-17.
[72]Zhao Qigang, Fang Xuming, Li Qunzhan. WNN-based NGN traffic prediction. Proceedings of 2005 International Symposium on Autonomous Decentralized Systems. Chengdu, China. USA, Institute of Electrical and Electronics Engineers Computer Society.2005, pp. 230-234.
[73]Wang Peng, Liu Yuan. Network traffic prediction based on improved BP wavelet neural network. Wireless Communications, Networking and Mobile Computing. Dalian, China. USA, Inst. of Elec. and Elec. Eng. Computer Society,2008, pp.1-5.
[74]雷霆,余镇危.一种网络流量预测的小波神经网络模型.计算机应用,2006,26(3)：526-528.
[75]李捷,候秀红,韩志杰.基于卡尔曼滤波和小波的网络流量预测算法研究,电子与信息学报,2007,29(3)：725-728.
[76]田妮莉,喻莉.一种基于小波变换和FIR神经网络的广域网网络流量预测模型.电子与信息学报,2008,30(10)：2499-2502.
[77]姚萌,刘渊,周刚.小波与神经网络相结合的网络流量预测模型.计算机工程与设计,2007,28(21)：5135-5136,5159.
[78]Feng Hailiang, Chen Di, Lin Qingjia, Chen Chunxiao. Multi-scale network traffic prediction using a two-stage neural network. IEEE International Conference On Wireless Communications, Networking And Mobile Computing. Wuhan, China.2006. USA. Inst. of Elec. and Elec. Eng. Computer Society.2006, Pp.1529-1533.
[79]洪炳熔,金飞虎,高庆吉.基于蚁群算法的多层前馈神经网络.哈尔滨工业大学学报,2003,35(7)：823-825.
[80]Gao Wei. Evolutionary neural network based on new ant colony algorithm. IEEE International Symposium on Computational Intelligence and Design. Wuhan, China.2008. USA. Inst. of Elec. and Elec. Eng. Computer Society.2008, Volume l, Pp.318-321.
[81]杨娜,付强,王淑丽等.小波神经网络模型的改进及其应用.系统工程理论与实践,2009,29(1)：168-173.
[82]Nikorn Pokudom. Determine of appropriate neural networks structure using ant colony system. ICROS-SICE International Joint Conference. Fukuoka International Congress Center, Japan.2009. USA, IEEE Computer Society.2009, Pp.4523-4525.
[83]Mohammed Tarique, Kemal E. Tepe, Sasan Adibi, Shervin Erfani. Survey of multipath routing protocols for mobile ad hoc networks. Journal of Network and Computer Applications.2009,32(2):1125-1143.
[84]安辉耀,卢锡城.移动自组网络多路径路由技术研究进展.计算机工程与科学,2006,4-7.
[85]张宝贤,刘越,陈常嘉.QoS路由的多路径算法.电子学报,2002,28(7)：120-122.
[86]Marc R Pearlman, Lygmunt J Haas. Peter Sholander, ct al. Alternate path routing in Mobile Ad Hoc Networks. Proceedings-IEEE Military Communications Conference MILCOM, 21st Century Military Communications Conference Proceedings MILCOM 2000. Los Angeles, CA, United states.2000, United States, Institute of Electrical and Electronics Engineers Inc.,2000, Pp.501-506.
[87]S J Lee, M Gerla. AODV-based Backup Routing in Ad hoc Network.2010 WRI International Conference on Communications and Mobile Computing, CMC 2010. Shenzhen, China. United States, IEEE Computer Society,2010, Pp.1311-1216.
[88]吴大鹏,甄岩,武穆清.基于路径分段的MANET自适应多径路由协议.电子与信息学报,2009,31(3)：698-701.
[89]Tracy Camp, Jeff Boleng, Vanessa Davies. Redundancy-Based Multi-path Routing in Ad hoc Networks. Computer Communications and Networks (ICCCN),1999 Proceedings of 8th International Conference on, Boston, MA, USA.1999, USA, Institute of Electrical and Electronics Engineers Inc., Oct.1999, Pp.524-529.
[90]J Raju, J J Garcia-Luna-acews. A New Approach to on-demand Loop-Free multipath Routing. Computer Communications and Networks,1999. Proceedings. Eight International Conference on, Boston, MA, USA.1999, USA, Institute of Electrical and Electronics Engineers Inc., Oct.1999, Pp.522-527.
[91]Marco Dorigo, Vittorio Maniezzo, Alberto Colorni. The Ant System:Optimization by a colony of cooperating agent. IEEE Transactions on Systems,1996,26(1):1-13.
[92]Goss S, Aron S, Deneubourg J L, et al. Self-organized shortcuts in the argentine ant. Naturewissen-schaften,1989,76(12):579-581.
[93]M Dorigo, LM.Gambardella. Ant Colony System:A cooperative learning approach to the traveling salesman problem. IEEE Transactions on Evolutionary Computation,1997, l(1):53-66.
[94]Stuetzle Thomas, Hoos Holger. MAX-MIN Ant system and local search for the traveling salesman problem. Proceedings of the IEEE International Conference on Evolutionary Computation, Indianapolis. Indianapolis, IN, USA.1997. USA, IEEE, Piscataway, NJ.1997, Pp.309-314.
[95]A Colorni, M Dorigo, V Maniezzo. Distributed optimization by ant colonies. Proceedings of ECAL91 European Conference on Artificial Life, Elsevier publishing, Pp.134-142.
[96]Macro Dorigo, Vittorio Maniezzo, Alberto Colorni. Ant system:optimization by a colony of cooperating agents. IEEE Trans. on systems man, and cybernetics-part B,1996(26):29-41.
[97]McCulloch W, Pitts W. A logical calculus of the ideas immanent in nervous activity. Bulletin of Mathematical Biophysics,1943,10(5):115-133.
[98]D. O. Hebb. The Organization of Behavior.Wiley, New York, New York,1949.
[99]F. Rosenblatt. The Perceptron:a probabilistic model for information storage and organization in the brain. Psychological Review,1958,65:386-408.
[100]Marvin Minsky and Seymour papert. Perceptron. Cambridge, MA:MIT press,1969.
[101]Hospfield J. J. Neural networks and physical systems with emergent collective computational abilities. National Academy of Science, USA (Biophysics),1982,79(6): 2554-2558.
[102]Hruschka H. Determining Market Response Functions by Neural Network Modeling. A Comparison to Econometric Techniques. European Journal of Operational Research,1993: 27-35.
[103]Chakraborty K., Mehrotra K., MohanCK, Ranka S.. Forecasting the behavior multivariate time series using neural networks. Neural Networks,1992, (5):961-970.
[104]A.Y.Yoon, A.G. Swales. Predicting stock price performance:a neural network approach. Proceedings of the Twenty-Fourth Hawaii International Conference on System Sciences, Kauai, HI, USA. Institute of Electrical and Electronics Engineers Inc..1991,4:156-162.
[105]李杰,王建中,胡红萍.基于PCA的BP神经网络股票预测研究.太原师范学院学报：自然科学版.2011,10(3)：60-63.
[106]丁晖.基于神经网络模型的人民币汇率预测研究.湖南大学博士论文,管理科学与工程,2008.
[107]刘玉娇,蒋传文.考虑负荷周期性和变化率的短期电价预测,电机与控制学报,2010,14(6)：21-26.
[108]孟凡青,解大.基于盲数和神经网络的电价预测模型,电力系统保护与控制,2009,16(2)：11-15,28.
[109]马君,刘小冬,孟颖.基于神经网络的城市交通流预测研究,电子学报,2009,37(5)：1029-1094.
[110]张德丰.MATLAB小波分析.北京,机械工业出版社,2008.50-51.
[111]M K Marina, S RDas. On-demand multipath distance vector routing in Ad hoc network. Network Protocols,2001 Ninth International Conference on, Riverside, CA, United states, 2001, USA. IEEE, IEEE Computer Society; IEEE Computer Society TCSE.2001, Pp. 14-23.
[112]Di Caro G, Dorigo M. Mobile agents for adaptive routing. Proceedings of the Hawaii International Conference on System Sciences. Big Island, HI, USA.1998. United States. Institute of Electrical and Electronics Engineers Computer Society, Los Alamitos, CA.1998, Pp.74-83.
[113]Dicaro G, Dorigom. AntNet:Distributed stigmergetic control for communications networks. Journal of Artificial Intelligence Research,1998,9(2):317-365.
[114]Dorigo M., Di Caro G, AntNet:a mobile agents approach to adaptive routing. Tech. Report, IRIDIA-Free Brussels University, Belgium,1997. htte://iridia.ulb.ac.bddoneo/ACO
[115]Mesut Gues, Udo Sorges, Imed Bouazizi, ARA-The ant-colony based routing algorithm for MANETs.2002 International Conference on Parallel Processing Workshops (ICPPW’02). Vancouver, B.C., Canada.2002, IEEE Computer Society.2002, Pp.79-85.
[116]吕勇,赵光宙,苏凡军.基于蚁群算法的自适应动态路由算法.浙江大学学报(工学版),2005,39(10)：1537-1540.
[117]刘永广,叶梧,冯穗力,庄宏成.基于蚂蚁算法的无线Mesh网公平路由算法.华南理工大学学报(自然科学版),2009,37(1)：119-123,129.
[118]张舜,许毅.基于蚁群算法的多QoS约束的多播路由优化算法.武汉理工大学学报(交通科学与工程版),2007,31(5)：939-942.
[119]吴正宇,宋瀚涛,姜少峰,梁野,徐晓梅.一种稳定的不相交多路径蚂蚁路由算法.北京理工大学学报,2007,27(4)：322-326.
[120]Baran B, Sosa R. AntNet:routing algorithm for data networks based on mobile agents. Argentine Symposium on Artificial Inteiligence,2000,12(3):75-84.
[121]Strobbe M, Verstraete V. Implementation and evaluation of AntNet, a distributed shortest-path algorithm. IEEE,2005,17(20):320-325.
[122]朱尚明,高大启.AntNet的多路径QOS路由算法研究.智能系统学报,2008,3(4)：349-354.
[123]吴博,江国星.基于蚁群算法的Ad hoc多径路由协议.计算机与数字工程,2007,35(8)：1-4.
[124]甘荣伟,蚁群优化算法及其应用研究.中上大学,博士学位论文,2009.
[125]Yudai Honma, Masaki Aida, Hideyuki Shimonishi, Atushi Iwata. A new multi-path routing methodology based on logit type assignment.2009 IEEE Globecom Workshops, Honolulu, HI, United states, IEEE Computer Society, United States, Pp.1-6.
[126]林国辉,马正新,王永前,曹志刚.基于蚂蚁算法的拥塞规避路由算法.清华大学学报(自然科学版),2003,43(1)：14.
[127]郑彦兴,田菁,窦文华.基于Pareto最优的QoS路由算法.软件学报,2005,16(8)：1484-1489.
[128]Floyd S, Jacobson V. Random early detection gateways for congestion avoidance. IEEE/ ACM Trans Networking,1993,1(2):397-413.
[129]Clark D, Fang W. Explicit allocation of best-effort packet delivery service. IEEE/ACM Transactions on Networking,1998,6(4):362-373
[130]Orozco J, Ros D. An adaptive RIO (A-RIO) queue management algorithm. In Proceedings of QoFIS 2003, No.2811 in Lecture Notes in Computer Science, Springer, October 2003.
[131]刘威,程文青,何建华等.区分服务网络中主动队列管理算法.软件学报,2005,16(6)：1120-1130.
[132]康亚男,张彩云,成汝震.DiffServ模型中主动队列管理研究.计算机工程与应用,2009,45(5)：125-128.
[133]Yang-Ick Joo, Kyeong Hur, Jong-Kook Kim, and Doo-Seop Eom, Yeonwoo Lee. RIO Configuration Optimization for Assured Service in DiffServ Networks. IEEE Transactions on Consumer Electronics, vol.55, No.4, Nov.2009, Pp.1968-1972.
[134]Fazlollahi Niloofar, Starobinski David. Distributed advance network reservation with delay guarantees.24th IEEE International Parallel and Distributed Processing Symposium (IPDPS 2010), Atlanta GA United states,19-23 Apr.2010, Pp.1-12.
[135]Luca Abeni, Luigi Palopoli, Claudio Scordino, Giuseppe Lipari. Resource reservations for general purpose applications. Industrial Informatics, IEEE Transactions on,2009, 5(1):12-21.
[136]Moonjeong Chang, Meejeong Lee, Hyunjeong Lee. An RSVP based seamless resource reservation scheme for wireless mobile networks. Computer Communications,2006, 30(l):81-92.
[137]Jiongkuan Hou, Yuguang Fang. Mobility-based channel reservation scheme for wireless mobile networks. Proc. of Wireless Communications and Networking Conference (WCNC'2000), Chicago, IL,23-28 Sep.2000, Vol.2. Pp.527-531.
[138]Somnath Sinha Maha Patra, Kousik Roy, Sarthak Banerjee, Deo Prakash Vidyarthi. Improved genetic algorithm for channel allocation with channel borrowing in mobile computing. Mobile computing, IEEE Transactions on,2006,5(7):884-892.
[139]Do Huu Tri, Vu Duy Loi, Ha Manh Dao, Improved frequency channel borrowing and locking algorithm in cellular mobile systems [C]. Advanced Communication Technology, 2009. ICACT 2009.11th International Conference on, Phoenix Park,15-18 Feb. 2009:214-217.
[140]Jiang H, Rappaport S S. CBWL:A new channel assignment and sharing method for cellular communication systems [J]. IEEE Trans Veh Technol,1994,43(2):313-322.
[141]Salman AlQahtani, Ashraf S. Mahmoud, Asrar U. Sheikh. Adaptive radio resource with borrowing for multi-operators 3G+wireless networks with heterogeneous traffic. Computer Communications, ELSEVIER,2006,29(15):2945-2951.
[142]王兆霞,孙雨耕,陈增强,袁著祉.基于模糊神经网络的网络业务流量预测研究.通信学报,2005,3(26)：136-140.
[143]Sang Aimin, Li Sanqi. A predictability analysis of network traffic. INFOCOM 2000, Nineteenth Annual Joint Conference of the IEEE Computer and Communications Societies. Tel Aviv, Israel.2000. USA, IEEE Service Center.2000, Vol.(1):342-351.
[144]Yu Guoqiang, Zhang Changshui. Switching ARIMA model based forecasting for traffic flow. IEEE International Conference on Proceedings of Acoustics, Speech, and Signal Processing. Montreal, Quebec, Canada.2004. The Institute of Electrical and Electronics Engineers Signal Processing Society,2004. Vol.2, Pp.429-432.
[145]金旗,裴昌幸,朱畅华ARIMA模型法分析网络流量.西安电子科技大学学报(自然科学版),2003,6(3)：6-10.
[146]贾亚会,干飞,纪宏广,田会礼.利用ARIMA模型预测我国煤油电的价格.中国矿业,2009,18(2)：82-85.
[147]蒋金良,林广明.基于ARIMA模型的自动站风速预测,控制理论与应用,2008,25(2)：374-376.
[148]张杰,刘小明,贺玉龙,陈永胜ARIMA模型在交通事故预测中的应用.北京工业大学学报,2007,33(12)：1295-1299.
[149]全林,朱建元.我国粮食价格对零售物价总水平影响的ARIMA模型分析.上海交通大学学报,1998,32(3)：70-78.
[150]Ning Liu, Shuzhen Nong, Jun Yan, Benyu Zhang, Zheng Chen, Ying Li. Similarity of temporal query logs based on arima model. Data Mining Workshops,2006. ICDM Workshops 2006. Sixth IEEE International Conference on, Dec.2006. Pp.366-370.
[151]王怡,付丽琴,韩焱.基于双BP神经网络数据融合的水声定位研究.核电子学与探测技术,2009,29(3)：676-679.
[152]焦李成.神经网络系统理论.西安电子科技大学出版社,1990：1-16.
[2]R.W. Thomas. Cognitive networks. Ph.D. dissertation. Virginia Polytechnic and State University, Blacksburg, VA,2007,58-60.
[3]Q. Mahmoud, Cognitive networks-towards self-aware networks. John Wiley and Sons,2007, ISBN 9780470061961.
[4]Clark David D., Partridge Craig, Christopher Ramming J., Wroclawski John T.. A knowledge plane for the internet. Proceedings of ACM SIGCOMM 2003 Conference on Computer Communications, Karlsruhe, Germany.2003. Association for Computing Machinery. Germany. Vol.33, No.4, pp.3-10.
[5]Thomas R, Friend D, Dasilva L. Cognitive networks:adaptation and learning to achieve end-to-end performance objectives. IEEE Communication Magazine.2006,44(12):51-57.
[6]Joseph Mitola III. Cognitive radio for flexible mobile multimedia communications. Mobile Networks and Applications.2001,6(5):435-441.
[7]Gelenbe E., Zhiguang Xu, Seref E.. Cognitive packet networks. Tools with Artificial Intelligence. Proceedings:11th IEEE International Conference on,1999, Chicago, IL, USA. IEEE Piscataway, NJ, United States.1999, pp.47-54.
[8]Thomas R.W., DaSilva L.A., Mackenzie A.B.. Cognitive networks. IEEE New Frontiers in Dynamic Spectrum Access Networks, DySPAN,8-11 Nov.2005:352-360.
[9]M. A. L. Thathachar, P. S. Sastry. Networks of Learning Automata, Kluwer,2004.
[10]Ryan W. Thomas, Daniel H. Friend, Luiz A. Dasilva, Allen B. Mackenzie. Cognitive networks:adaptation and learning to achieve end-to-end performance objectives. Communications Magazine IEEE.2006,44(12):51-57.
[11]Mitola J. III. Software Radios:Wireless architectures for the 21st century. Fairfax, VA: Statisfaction,1999.
[12]冯光升,王慧强,马春光,李冰洋,赵倩.面向认知网络的用户QoS动态自配置方法.通信学报,2010,31(3)：133-140.
[13]陈铮,张勇,滕颖蕾,罗希.认知网络概述.无线通信技术,2009,4：21-25,29
[14]Ron Banner and Ariel Orda. Muttipath routing algorithms for congestion minimization. IEEE/ACM Transactions on Networking, Vol.15, No.2,2007, pp.413-424.
[15]李红艳,李建东,周丹.认知网络路由技术.中兴通讯技术,2010,16(1)：50-52.
[16]Perkins CE, Bhagwat P. Highly dynamic destination sequence distance vector (DSDV) routing for mobile computers, In:Proceedings of the ACM SIGCOMM, London, UK,1994.
[17]Broch J, Johnson DB, Maltz DA. The dynamic source routing protocol for mobile ad hoc networks. IETF Internet-draft,1998.
[18]Perkins CE. Ad hoc on-demand distance vector (AODV) routing. IETF Internet-draft,1997.
[19]Anurag K, Manjunath D, Kuri J. Communication networking:an analytical approach. Los Altos, CA:Morgan Kaufmann Publishers,2004. pp.715-716.
[20]Bertsekas D, Gallager R. Data networks,2nd ed. Englewood Cliffs, NJ:Prentice-Hall,1992, pp.162-169.
[21]Pham PP, Perrau S. Performance analysis of reactive shortest path and multipath routing mechanism with load balance. In:Proceedings of the IEEE INFOCOM.2003, San Francisco, California, USA. July 2003, pp.251-259.
[22]Tsirigos A, Haas ZJ, Tabrizi SS. Multipath routing in mobile ad hoc networks or how to route in the presence of frequent topology changes. In:Proceedings of the military communications conference, McLean, VA, United states,2001, Institute of Electrical and Electronics Engineers Inc., October 2001, vol.2, pp.878-883.
[23]John Moy. RFC 2328. OSPF Version 2, IETF,1998.
[24]Jing F, Bhuvaneswaran RS, Katayama Y, Takahashi N. A multipath on-demand routing with path selection probabilities for mobile ad hoc networks. In:Proceedings of the international conference on wireless communications, networking and mobile computing. Wuhan, China. USA. Institute of Electrical and Electronics Engineers Computer Society.2005, vol.2, pp. 1099-1102.
[25]Ye Z, Krishnamurthy SV, Tripathi SK. A framework for reliable routing in mobile ad hoc networks. In:Proceedings of the 22nd annual joint conference of the IEEE computer and communications societies (INFOCOM).2003, San Francisco, CA, United states. Institute of Electrical and Electronics Engineers Inc..2003, vol.1, pp.270-280.
[26]Huang X, Fang Y. End-to-end delay differentiation by prioritized multipath routing in wireless sensor networks. In:Military communications conference. Atlatnic City, NJ, United states. USA. Institute of Electrical and Electronics Engineers Inc..2005, vol.2, pp. 1277-1283.
[27]Popa L, Raiciu C, Stoica I, Rosenblum DS. Reducing congestion effects in wireless networks by multipath routing. In:Proceeding of the 14th IEEE international conference on network protocols. Santa Barbara, California, USA.2006. United states. IEEE Computer Society.2006, pp.96-104.
[28]Li X, Cuthbert L. Stable node-disjoint multipath routing with low overhead in mobile ad hoc networks. In:Proceedings of the IEEE computer society's 12th annual international symposium on modeling, analysis, and simulation of computer and telecommunications systems (MASCOTS 2004). Volendam, Netherlands.2004, USA. IEEE Computer Society. 2004, pp.184-191.
[29]Lou W. An efficient N-to-1 multipath routing protocol in wireless sensor networks. In: Proceedings of the IEEE international conference on mobile ad hoc and sensor systems conference. Washington, DC.2005. USA. Institute of Electrical and Electronics Engineers Computer Society.2005, pp.665-672.
[30]Mao S, Lin S, Wang Y, Panwar SS, Li Y. Multipath video transport over ad hoc networks. IEEE Wireless Communication.2005,12(4):42-49.
[31]Nasipuri A, Das SR. On-demand multipath routing for mobile ad hoc networks. In: Proceedings of the 8th international conference on computer communications and networks, Boston, MA, USA.1999, USA, Institute of Electrical and Electronics Engineers Inc., Oct. 1999. pp.64-70.
[32]Lee S.J., Gerla M.. Split multipath routing with maximally disjoint paths in ad hoc networks. Communications. IEEE International Conference on, Helsinki, Finland.2001, USA. Institute of Electrical and Electronics Engineers Inc.. vol.10, pp.3201-3205.
[33]Wisitpongphan N, Tonguz OK. Disjoint multipath source routing in ad hoc networks: transport capacity. In:Proceedings of the IEEE 58th vehicular technology conference (VTC), Orlando, FL, United states. October 2003. USA. Institute of Electrical and Electronics Engineers Inc..2003. vol.4, pp.2207-2211.
[34]Panichpapiboon S, Ferrai G, Wisitpongphan N, Tonguz OK. Route reservation in ad hoc networks:Is it a good idea. In:Proceedings of the IEEE wireless communication and networking conference (WCNC), Orleans, LA.2005. USA. Institute of Electrical and Electronics Engineers Inc..2005. vol.4, pp.2045-2050.
[35]Dulman S, Wu J, Havinga P. An energy efficient multipath routing algorithm for wireless sensor networks. In:Proceedings of the 6th international symposium on autonomous decentralized systems with an emphasis on advanced distributed transportation systems, Pisa, Italy.2010. USA, IEEE Computer Society.2010, pp.251-256.
[36]Liang Y, Midkiff SF. Multipath Fresnel zone routing for wireless ad hoc networks. In: Proceedings of the IEEE wireless communications and networking conference, New Orleans, LA, United states.2005. USA. Institute of Electrical and Electronics Engineers Inc.. 2005. vol.4, pp.1958-1963.
[37]Ganesan D, Govindan R, Shenker S, Estrin D. Highly-resilient, energy-efficient multipath routing in wireless sensor networks. ACM SIGMOBILE Mobile Computing and Communications Review.2001,5(4):11-25.
[38]舒炎泰,高德云,王雷.无线ad hoc网络中的多径源路由.电子学报,2002,30(2)：279-282.
[39]Wei W, Zakhor A. Robust multipath source routing protocol (RMPSR) for video communication over wireless ad hoc networks. In:IEEE international conference on multimedia and expo, Taipei, Taiwan.2004. USA. Institute of Electrical and Electronics Engineers Inc.2004, vol.2, pp.1379-1382.
[40]Yao Z, Jiang J, Fan P, Cao Z, Li VOK. A neighbor table based multipath routing in ad hoc networks. In:57th IEEE semiannual vehicular technology conference, Jeju, Republic of Korea.2003. USA, Institute of Electrical and Electronics Engineers Inc..2003, vol.3, pp. 1739-1743.
[41]Patrick McCarthy. Dan Grigoras. Multipath associativity based routing. In:Proceedings of the second annual conference on wireless on-demand network systems and services (WONS), St. Moritz, Switzerland, USA, IEEE Computer Society.2005. pp.60-69.
[42]Islam Beltagy, Moustafa Youssef, Mohamed El-Derini. A new routing metric and protocol for multipath routing in cognitive networks. Metric,2011 March,974-979.
[43]Richard E. Tuggle. Cognitive multipath routing for mission critical multi-hop wireless networks.42nd South Eastern Symposium on System Theory University of Texas at Tyler Tyler, TX, USA, March 7-9,2010. Pp.66-71
[44]Suyang Ju, Josehp B Evans. Cognitive multipath multi-channel routing protocol for mobile ad-hoc networks.2010 IEEE Global Telecommunications Conference, GLOBECOM 2010. December 2010. Miami, FL, United states, Pp.1-6.
[45]Dave Clark, Scott Shenker, Lixia Zhang, Deborah Estrin, Sugih Jamin, John Wroclawski, Shai Herzog, Bob Braden. Integrated services in the Internet architecture:An overview. RFC 1633, Jun.1994.
[46]Blake S, Black D, Carlson M, Davies E, Wang Z, Weiss W. An architecture for differentiated services. IETF RFC 2475,1998.
[47]R. Braden Ed., L. Zhang, S. Berson, S. Herzog, S. Jamin. ResourceReser Vation Protocol-Versionl Functional Specification. RFC2205, September 1997.
[48]Long Keping, Cheng Shiduan, Ma Jian. Internet QoS:architectures, Strategies and Mechanisms. High Technology Letters,2001,7(1):13-21.
[49]张知皦.移动网络资源预留QoS技术研究.硕士研究生学位论文.国防科学技术大学图书馆,国防科学技术大学,2003年,Pp.2-27.
[50]Mauthe Andreas, Garcia Francisco, Hutchison David, Yeadon Nicholas. QoS filtering and resource reservation in an internet environment, Multimedia Tools and Applications, vol.13, no.3, March 2001, Pp.285-306.
[51]冯径,承彦,顾冠群.支持适应性路由选择的资源预留协议扩展研究.计算机集成制造系统-CIMS.2002,8(2):155-161.
[52]郭勐,张拥军,彭宇行.一种基于RSVP协议的资源提前保留技术.计算机应用研究.2004,21(2)：238-240.
[53]Terzis A., Krawczyk J., Wroclawski J., Zhang L.. RSVP Operation Over IP Tunnels. RFC 2746, January 2000.
[54]P. Pan, E. Hahne, H. Schulzrinne. BGRP:A tree-based aggregation protocol for inter-domain reservations. Journal of Communication and Networks.2000,2(2):157-167.
[55]R Bless. Towards scalable management of Qos-based end-to-end services. Proc. IEEE Symposium Record on Network Operations and Management Symposium. Seoul, Republic of Korea.2004, USA.Institute of Electrical and Electronics Engineers Inc..2004, Vol.1, pp. 293-306.
[56]Bongkyo Moon, Hamid Aghvami. Quality-of-Service mechanisms in all-IP wireless access networks. IEEE Journal on Selected Areas in Communications.2004,22(5):873-888.
[57]孙毅,张玉成,冯斌,方更法,石晶林,Dutkiewicz Eryk. RSVP协议在移动IPv6网络中的扩展性研究.软件学报,2008,19(7)：1731-1742.
[58]童一飞,李东波.基于资源预测的网格资源预留机制研究.系统仿真学报.2009,21(2)：432-436.
[59]胡春明,怀进鹏,沃天宇.一种基于松弛时间的服务网格资源能力预留机制.计算机研究与发展,2007,44(1)：20-28.
[60]梁泉,杨扬,王元卓.服务网格中基于请求生命期的资源预留方法和策略.控制与决策,2008,23(4)：403-408.
[61]蒲静.基于任务可分的网格资源预留机制,计算机工程与应用,2008,44(12)：118-120,138.
[62]金旗,裴昌幸,朱畅华.ARIMA模型法分析网络流量.西安电子科技大学学报(自然科学版),2003,6(3)：6-10.
[63]Yu Guoqiang, Zhang Changshui. Switching ARIMA model based forecasting for traffic flow. IEEE International Conference on Acoustics, Speech, and Signal Processing. Montreal, Que, Canada.2004, USA, Institute of Electrical and Electronics Engineers Inc..2004, Vol.2, Pp. 429-432.
[64]Sang Aimin, Li Sanqi. A predictability analysis of network traffic. Computer Networks, Elsevier.2002,39(4):329-345.
[65]Gao Chuanshan, Han Liangxiu,Cen Zhiwei, Chu Chunbo. A new multi fractal traffic model based on the wavelet transform. Proceedings of the ISCA 14th International Conference: Parallel and Distributed Computing Systems, Richardson, Texas USA.2001, USA, Association for Computing Machinery.2001. Pp.157-162.
[66]W E Leland, M S Taqqu, W Willinger, D V Wilson. On the self-similar nature of Ethernet traffic (extended version). IEEE/ACM Transactions on Networking,1994,2(1):1-15.
[67]V Paxson, S Floyd. Wide-area traffic:The failure of Poisson modeling. IEEE/ACM Transactions on Networking,1995,3(3):226-244.
[68]Husmeier D, Taylor J G Neural networks for predicting conditional probability densities: improved training scheme combining EM and RVF. Neural Networks,1998,11(1):89,116.
[69]Hussein D. An object-oriented neural network approach to short-term traffic forecasting. European of Operational Research,2001,131(2):253-261.
[70]Wakurah, Zurada JM. Bi-directional computing architecture for time series prediction. Neural Networks,2001,14(9):1307-1321.
[71]De Keyser R M C. et al. A Self-tuning Multi-step. Predictior Application Automatica.1981, 117(1):167-17.
[72]Zhao Qigang, Fang Xuming, Li Qunzhan. WNN-based NGN traffic prediction. Proceedings of 2005 International Symposium on Autonomous Decentralized Systems. Chengdu, China. USA, Institute of Electrical and Electronics Engineers Computer Society.2005, pp. 230-234.
[73]Wang Peng, Liu Yuan. Network traffic prediction based on improved BP wavelet neural network. Wireless Communications, Networking and Mobile Computing. Dalian, China. USA, Inst. of Elec. and Elec. Eng. Computer Society,2008, pp.1-5.
[74]雷霆,余镇危.一种网络流量预测的小波神经网络模型.计算机应用,2006,26(3)：526-528.
[75]李捷,候秀红,韩志杰.基于卡尔曼滤波和小波的网络流量预测算法研究,电子与信息学报,2007,29(3)：725-728.
[76]田妮莉,喻莉.一种基于小波变换和FIR神经网络的广域网网络流量预测模型.电子与信息学报,2008,30(10)：2499-2502.
[77]姚萌,刘渊,周刚.小波与神经网络相结合的网络流量预测模型.计算机工程与设计,2007,28(21)：5135-5136,5159.
[78]Feng Hailiang, Chen Di, Lin Qingjia, Chen Chunxiao. Multi-scale network traffic prediction using a two-stage neural network. IEEE International Conference On Wireless Communications, Networking And Mobile Computing. Wuhan, China.2006. USA. Inst. of Elec. and Elec. Eng. Computer Society.2006, Pp.1529-1533.
[79]洪炳熔,金飞虎,高庆吉.基于蚁群算法的多层前馈神经网络.哈尔滨工业大学学报,2003,35(7)：823-825.
[80]Gao Wei. Evolutionary neural network based on new ant colony algorithm. IEEE International Symposium on Computational Intelligence and Design. Wuhan, China.2008. USA. Inst. of Elec. and Elec. Eng. Computer Society.2008, Volume l, Pp.318-321.
[81]杨娜,付强,王淑丽等.小波神经网络模型的改进及其应用.系统工程理论与实践,2009,29(1)：168-173.
[82]Nikorn Pokudom. Determine of appropriate neural networks structure using ant colony system. ICROS-SICE International Joint Conference. Fukuoka International Congress Center, Japan.2009. USA, IEEE Computer Society.2009, Pp.4523-4525.
[83]Mohammed Tarique, Kemal E. Tepe, Sasan Adibi, Shervin Erfani. Survey of multipath routing protocols for mobile ad hoc networks. Journal of Network and Computer Applications.2009,32(2):1125-1143.
[84]安辉耀,卢锡城.移动自组网络多路径路由技术研究进展.计算机工程与科学,2006,4-7.
[85]张宝贤,刘越,陈常嘉.QoS路由的多路径算法.电子学报,2002,28(7)：120-122.
[86]Marc R Pearlman, Lygmunt J Haas. Peter Sholander, ct al. Alternate path routing in Mobile Ad Hoc Networks. Proceedings-IEEE Military Communications Conference MILCOM, 21st Century Military Communications Conference Proceedings MILCOM 2000. Los Angeles, CA, United states.2000, United States, Institute of Electrical and Electronics Engineers Inc.,2000, Pp.501-506.
[87]S J Lee, M Gerla. AODV-based Backup Routing in Ad hoc Network.2010 WRI International Conference on Communications and Mobile Computing, CMC 2010. Shenzhen, China. United States, IEEE Computer Society,2010, Pp.1311-1216.
[88]吴大鹏,甄岩,武穆清.基于路径分段的MANET自适应多径路由协议.电子与信息学报,2009,31(3)：698-701.
[89]Tracy Camp, Jeff Boleng, Vanessa Davies. Redundancy-Based Multi-path Routing in Ad hoc Networks. Computer Communications and Networks (ICCCN),1999 Proceedings of 8th International Conference on, Boston, MA, USA.1999, USA, Institute of Electrical and Electronics Engineers Inc., Oct.1999, Pp.524-529.
[90]J Raju, J J Garcia-Luna-acews. A New Approach to on-demand Loop-Free multipath Routing. Computer Communications and Networks,1999. Proceedings. Eight International Conference on, Boston, MA, USA.1999, USA, Institute of Electrical and Electronics Engineers Inc., Oct.1999, Pp.522-527.
[91]Marco Dorigo, Vittorio Maniezzo, Alberto Colorni. The Ant System:Optimization by a colony of cooperating agent. IEEE Transactions on Systems,1996,26(1):1-13.
[92]Goss S, Aron S, Deneubourg J L, et al. Self-organized shortcuts in the argentine ant. Naturewissen-schaften,1989,76(12):579-581.
[93]M Dorigo, LM.Gambardella. Ant Colony System:A cooperative learning approach to the traveling salesman problem. IEEE Transactions on Evolutionary Computation,1997, l(1):53-66.
[94]Stuetzle Thomas, Hoos Holger. MAX-MIN Ant system and local search for the traveling salesman problem. Proceedings of the IEEE International Conference on Evolutionary Computation, Indianapolis. Indianapolis, IN, USA.1997. USA, IEEE, Piscataway, NJ.1997, Pp.309-314.
[95]A Colorni, M Dorigo, V Maniezzo. Distributed optimization by ant colonies. Proceedings of ECAL91 European Conference on Artificial Life, Elsevier publishing, Pp.134-142.
[96]Macro Dorigo, Vittorio Maniezzo, Alberto Colorni. Ant system:optimization by a colony of cooperating agents. IEEE Trans. on systems man, and cybernetics-part B,1996(26):29-41.
[97]McCulloch W, Pitts W. A logical calculus of the ideas immanent in nervous activity. Bulletin of Mathematical Biophysics,1943,10(5):115-133.
[98]D. O. Hebb. The Organization of Behavior.Wiley, New York, New York,1949.
[99]F. Rosenblatt. The Perceptron:a probabilistic model for information storage and organization in the brain. Psychological Review,1958,65:386-408.
[100]Marvin Minsky and Seymour papert. Perceptron. Cambridge, MA:MIT press,1969.
[101]Hospfield J. J. Neural networks and physical systems with emergent collective computational abilities. National Academy of Science, USA (Biophysics),1982,79(6): 2554-2558.
[102]Hruschka H. Determining Market Response Functions by Neural Network Modeling. A Comparison to Econometric Techniques. European Journal of Operational Research,1993: 27-35.
[103]Chakraborty K., Mehrotra K., MohanCK, Ranka S.. Forecasting the behavior multivariate time series using neural networks. Neural Networks,1992, (5):961-970.
[104]A.Y.Yoon, A.G. Swales. Predicting stock price performance:a neural network approach. Proceedings of the Twenty-Fourth Hawaii International Conference on System Sciences, Kauai, HI, USA. Institute of Electrical and Electronics Engineers Inc..1991,4:156-162.
[105]李杰,王建中,胡红萍.基于PCA的BP神经网络股票预测研究.太原师范学院学报：自然科学版.2011,10(3)：60-63.
[106]丁晖.基于神经网络模型的人民币汇率预测研究.湖南大学博士论文,管理科学与工程,2008.
[107]刘玉娇,蒋传文.考虑负荷周期性和变化率的短期电价预测,电机与控制学报,2010,14(6)：21-26.
[108]孟凡青,解大.基于盲数和神经网络的电价预测模型,电力系统保护与控制,2009,16(2)：11-15,28.
[109]马君,刘小冬,孟颖.基于神经网络的城市交通流预测研究,电子学报,2009,37(5)：1029-1094.
[110]张德丰.MATLAB小波分析.北京,机械工业出版社,2008.50-51.
[111]M K Marina, S RDas. On-demand multipath distance vector routing in Ad hoc network. Network Protocols,2001 Ninth International Conference on, Riverside, CA, United states, 2001, USA. IEEE, IEEE Computer Society; IEEE Computer Society TCSE.2001, Pp. 14-23.
[112]Di Caro G, Dorigo M. Mobile agents for adaptive routing. Proceedings of the Hawaii International Conference on System Sciences. Big Island, HI, USA.1998. United States. Institute of Electrical and Electronics Engineers Computer Society, Los Alamitos, CA.1998, Pp.74-83.
[113]Dicaro G, Dorigom. AntNet:Distributed stigmergetic control for communications networks. Journal of Artificial Intelligence Research,1998,9(2):317-365.
[114]Dorigo M., Di Caro G, AntNet:a mobile agents approach to adaptive routing. Tech. Report, IRIDIA-Free Brussels University, Belgium,1997. htte://iridia.ulb.ac.bddoneo/ACO
[115]Mesut Gues, Udo Sorges, Imed Bouazizi, ARA-The ant-colony based routing algorithm for MANETs.2002 International Conference on Parallel Processing Workshops (ICPPW’02). Vancouver, B.C., Canada.2002, IEEE Computer Society.2002, Pp.79-85.
[116]吕勇,赵光宙,苏凡军.基于蚁群算法的自适应动态路由算法.浙江大学学报(工学版),2005,39(10)：1537-1540.
[117]刘永广,叶梧,冯穗力,庄宏成.基于蚂蚁算法的无线Mesh网公平路由算法.华南理工大学学报(自然科学版),2009,37(1)：119-123,129.
[118]张舜,许毅.基于蚁群算法的多QoS约束的多播路由优化算法.武汉理工大学学报(交通科学与工程版),2007,31(5)：939-942.
[119]吴正宇,宋瀚涛,姜少峰,梁野,徐晓梅.一种稳定的不相交多路径蚂蚁路由算法.北京理工大学学报,2007,27(4)：322-326.
[120]Baran B, Sosa R. AntNet:routing algorithm for data networks based on mobile agents. Argentine Symposium on Artificial Inteiligence,2000,12(3):75-84.
[121]Strobbe M, Verstraete V. Implementation and evaluation of AntNet, a distributed shortest-path algorithm. IEEE,2005,17(20):320-325.
[122]朱尚明,高大启.AntNet的多路径QOS路由算法研究.智能系统学报,2008,3(4)：349-354.
[123]吴博,江国星.基于蚁群算法的Ad hoc多径路由协议.计算机与数字工程,2007,35(8)：1-4.
[124]甘荣伟,蚁群优化算法及其应用研究.中上大学,博士学位论文,2009.
[125]Yudai Honma, Masaki Aida, Hideyuki Shimonishi, Atushi Iwata. A new multi-path routing methodology based on logit type assignment.2009 IEEE Globecom Workshops, Honolulu, HI, United states, IEEE Computer Society, United States, Pp.1-6.
[126]林国辉,马正新,王永前,曹志刚.基于蚂蚁算法的拥塞规避路由算法.清华大学学报(自然科学版),2003,43(1)：14.
[127]郑彦兴,田菁,窦文华.基于Pareto最优的QoS路由算法.软件学报,2005,16(8)：1484-1489.
[128]Floyd S, Jacobson V. Random early detection gateways for congestion avoidance. IEEE/ ACM Trans Networking,1993,1(2):397-413.
[129]Clark D, Fang W. Explicit allocation of best-effort packet delivery service. IEEE/ACM Transactions on Networking,1998,6(4):362-373
[130]Orozco J, Ros D. An adaptive RIO (A-RIO) queue management algorithm. In Proceedings of QoFIS 2003, No.2811 in Lecture Notes in Computer Science, Springer, October 2003.
[131]刘威,程文青,何建华等.区分服务网络中主动队列管理算法.软件学报,2005,16(6)：1120-1130.
[132]康亚男,张彩云,成汝震.DiffServ模型中主动队列管理研究.计算机工程与应用,2009,45(5)：125-128.
[133]Yang-Ick Joo, Kyeong Hur, Jong-Kook Kim, and Doo-Seop Eom, Yeonwoo Lee. RIO Configuration Optimization for Assured Service in DiffServ Networks. IEEE Transactions on Consumer Electronics, vol.55, No.4, Nov.2009, Pp.1968-1972.
[134]Fazlollahi Niloofar, Starobinski David. Distributed advance network reservation with delay guarantees.24th IEEE International Parallel and Distributed Processing Symposium (IPDPS 2010), Atlanta GA United states,19-23 Apr.2010, Pp.1-12.
[135]Luca Abeni, Luigi Palopoli, Claudio Scordino, Giuseppe Lipari. Resource reservations for general purpose applications. Industrial Informatics, IEEE Transactions on,2009, 5(1):12-21.
[136]Moonjeong Chang, Meejeong Lee, Hyunjeong Lee. An RSVP based seamless resource reservation scheme for wireless mobile networks. Computer Communications,2006, 30(l):81-92.
[137]Jiongkuan Hou, Yuguang Fang. Mobility-based channel reservation scheme for wireless mobile networks. Proc. of Wireless Communications and Networking Conference (WCNC'2000), Chicago, IL,23-28 Sep.2000, Vol.2. Pp.527-531.
[138]Somnath Sinha Maha Patra, Kousik Roy, Sarthak Banerjee, Deo Prakash Vidyarthi. Improved genetic algorithm for channel allocation with channel borrowing in mobile computing. Mobile computing, IEEE Transactions on,2006,5(7):884-892.
[139]Do Huu Tri, Vu Duy Loi, Ha Manh Dao, Improved frequency channel borrowing and locking algorithm in cellular mobile systems [C]. Advanced Communication Technology, 2009. ICACT 2009.11th International Conference on, Phoenix Park,15-18 Feb. 2009:214-217.
[140]Jiang H, Rappaport S S. CBWL:A new channel assignment and sharing method for cellular communication systems [J]. IEEE Trans Veh Technol,1994,43(2):313-322.
[141]Salman AlQahtani, Ashraf S. Mahmoud, Asrar U. Sheikh. Adaptive radio resource with borrowing for multi-operators 3G+wireless networks with heterogeneous traffic. Computer Communications, ELSEVIER,2006,29(15):2945-2951.
[142]王兆霞,孙雨耕,陈增强,袁著祉.基于模糊神经网络的网络业务流量预测研究.通信学报,2005,3(26)：136-140.
[143]Sang Aimin, Li Sanqi. A predictability analysis of network traffic. INFOCOM 2000, Nineteenth Annual Joint Conference of the IEEE Computer and Communications Societies. Tel Aviv, Israel.2000. USA, IEEE Service Center.2000, Vol.(1):342-351.
[144]Yu Guoqiang, Zhang Changshui. Switching ARIMA model based forecasting for traffic flow. IEEE International Conference on Proceedings of Acoustics, Speech, and Signal Processing. Montreal, Quebec, Canada.2004. The Institute of Electrical and Electronics Engineers Signal Processing Society,2004. Vol.2, Pp.429-432.
[145]金旗,裴昌幸,朱畅华ARIMA模型法分析网络流量.西安电子科技大学学报(自然科学版),2003,6(3)：6-10.
[146]贾亚会,干飞,纪宏广,田会礼.利用ARIMA模型预测我国煤油电的价格.中国矿业,2009,18(2)：82-85.
[147]蒋金良,林广明.基于ARIMA模型的自动站风速预测,控制理论与应用,2008,25(2)：374-376.
[148]张杰,刘小明,贺玉龙,陈永胜ARIMA模型在交通事故预测中的应用.北京工业大学学报,2007,33(12)：1295-1299.
[149]全林,朱建元.我国粮食价格对零售物价总水平影响的ARIMA模型分析.上海交通大学学报,1998,32(3)：70-78.
[150]Ning Liu, Shuzhen Nong, Jun Yan, Benyu Zhang, Zheng Chen, Ying Li. Similarity of temporal query logs based on arima model. Data Mining Workshops,2006. ICDM Workshops 2006. Sixth IEEE International Conference on, Dec.2006. Pp.366-370.
[151]王怡,付丽琴,韩焱.基于双BP神经网络数据融合的水声定位研究.核电子学与探测技术,2009,29(3)：676-679.
[152]焦李成.神经网络系统理论.西安电子科技大学出版社,1990：1-16.