IP网络流量变权组合预测模型研究
|
摘要
随着Internet及其应用的迅速发展,网络开始承载越来越多的应用服务,网络行为特征日趋复杂,这给网络规划、网络管理以及服务质量带来了越来越大挑战。IP网络流量建模及预测是带宽分配、流量工程、性能分析、路由控制及差错控制的基础和主要参考依据。
本文首先分析了IP网络流量的主要特性,分析比较了几种传统的IP网络流量预测模型的优缺点,在此基础上提出了基于残差改进的灰色预测模型,该模型通过对灰色模型的残差序列做指数化处理,从而使得正负交替序列向非负序列转化。实验结果表明,改进后的模型具有较高的预测精度。针对常权组合模型的权值恒定不变,很难精确预测现实网络流量的问题,本文提出了模糊自适应的变权组合预测模型,该模型由改进后的残差灰色模型和BP神经网络模型组成,引入模糊决策机制和自适应机制,通过对数据的处理得到组合模型中单一模型的模糊权值和基本权值,然后计算得出该单一模型在组合模型中的权值。实验结果表明,模糊自适应的变权组合预测模型与常权组合预测模型相比,性能更优。但实验同时也发现,在小时间粒度网络流量预测中,当预测步长超过7步以后,预测误差超过20%。针对此问题,本文提出了动态变权组合预测模型,即在原模型的基础上引入动态机制。当预测误差超过设定阀值时,变权组合预测模型也随之进行重构,从而减少预测误差。实验结果表明,动态变权组合预测模型比原模型在预测步长上有所增长。
As the rapid development and application of Internet, the scale of internet is becoming larger and larger, the features of network behavior are becoming complicated increasingly, which brings a great challenge to network planning、network management and quality of service. Predicting and modeling network traffic can bring out essential reference for bandwidth allocation, network traffic control, routing control, entry control and error control in network management.
In the beginning, the article analyze the main character about network, then analyze and compare the advantage and disadvantage of some traditional network analytic model. After these analysis, a kind of grey predicting method based on error was given, which greatly improves the original residual error model via index processing on error sequence. And this new model was proved higher prediction accuracy by the experimental results. In the following, aiming at the shortages of combination Model based on Constant weight, a new model of combined forecasting method based on Fuzzy Adaptive variable weight was brought out, which uses fuzzy decision-making mechanism and the adaptive mechanism to gain the single model’s fuzzy weights and the basic weight, Experimental results show that the model of combined forecasting method based on Fuzzy Adaptive variable weight is better than the combination Model based on Constant weight in the performance .But at the same time, when forecasting more than 7-step in the small time granularity network traffic prediction,, the prediction error will more than 20%, and have become a big trend. On the basis of the original model by adding dynamic mechanism, when the prediction error reaches a certain characteristic value, the variable weight combination model also will be reconstructed to adjust, thereby reducing the prediction error. Experimental results show that the dynamic variable weight combination forecasting model is better than the original model on the step size increased.
本文首先分析了IP网络流量的主要特性,分析比较了几种传统的IP网络流量预测模型的优缺点,在此基础上提出了基于残差改进的灰色预测模型,该模型通过对灰色模型的残差序列做指数化处理,从而使得正负交替序列向非负序列转化。实验结果表明,改进后的模型具有较高的预测精度。针对常权组合模型的权值恒定不变,很难精确预测现实网络流量的问题,本文提出了模糊自适应的变权组合预测模型,该模型由改进后的残差灰色模型和BP神经网络模型组成,引入模糊决策机制和自适应机制,通过对数据的处理得到组合模型中单一模型的模糊权值和基本权值,然后计算得出该单一模型在组合模型中的权值。实验结果表明,模糊自适应的变权组合预测模型与常权组合预测模型相比,性能更优。但实验同时也发现,在小时间粒度网络流量预测中,当预测步长超过7步以后,预测误差超过20%。针对此问题,本文提出了动态变权组合预测模型,即在原模型的基础上引入动态机制。当预测误差超过设定阀值时,变权组合预测模型也随之进行重构,从而减少预测误差。实验结果表明,动态变权组合预测模型比原模型在预测步长上有所增长。
As the rapid development and application of Internet, the scale of internet is becoming larger and larger, the features of network behavior are becoming complicated increasingly, which brings a great challenge to network planning、network management and quality of service. Predicting and modeling network traffic can bring out essential reference for bandwidth allocation, network traffic control, routing control, entry control and error control in network management.
In the beginning, the article analyze the main character about network, then analyze and compare the advantage and disadvantage of some traditional network analytic model. After these analysis, a kind of grey predicting method based on error was given, which greatly improves the original residual error model via index processing on error sequence. And this new model was proved higher prediction accuracy by the experimental results. In the following, aiming at the shortages of combination Model based on Constant weight, a new model of combined forecasting method based on Fuzzy Adaptive variable weight was brought out, which uses fuzzy decision-making mechanism and the adaptive mechanism to gain the single model’s fuzzy weights and the basic weight, Experimental results show that the model of combined forecasting method based on Fuzzy Adaptive variable weight is better than the combination Model based on Constant weight in the performance .But at the same time, when forecasting more than 7-step in the small time granularity network traffic prediction,, the prediction error will more than 20%, and have become a big trend. On the basis of the original model by adding dynamic mechanism, when the prediction error reaches a certain characteristic value, the variable weight combination model also will be reconstructed to adjust, thereby reducing the prediction error. Experimental results show that the dynamic variable weight combination forecasting model is better than the original model on the step size increased.
引文
[1] Khotanzad A, Sadek N. Multi-scale high-speed network flow prediction using combination of neural networks [J]. Proceedings of the International Joint Conference on Neural Networks, 2003, (2):1071-1075.
[2] Chen BS ,Pen SC, Wang KC. Flow modeling, prediction and congestion control for high-speed networks: A Fuzzy AR Approach [J]. IEEE Trans. On Fuzzy System, 2000, (8): 491-508.
[3] Mannersalo P. Gaussian and muhfractal processes in teletrattlc theory. PhD dissertation[EB].ESP0020003, V1T Publications 491, ISBN 951-6037–X (URL:http: //www.inf.vtt.inf/pdf/).
[4] Erramilli A, RouIghall M, Veitch D, Willinger W. Serf-similar traffic and network dynamics [J]. Proceedings of the IEEE.2002(5):90-96.
[5] Capp O, Moulines E. Long range dependence and heavy tail modeling for telegraphic data [J]. 2002(1):10-13.
[6] Wu G, Chong EKP, Givan R. Congestion control via online sampling. Proceedings of the 2001 IEEE Infocom Anchorage [J], AK.2001(4):1271-1280.
[7] Wang S, Xuan D, Bettati R, etal. Providing absolute differentiated services for real time application in static priority scheduling Networks [C]. Proceedings of the 2001 IEEE Infocom Anchorage, AK.2001.
[8] Feldman n A, Greenberg A, Lund C, etal. Netscop:traffic engineering for IP network [M]. IEEE Network Magazine.2000.
[9] Parson V. End-to-End routing behavior in the Internet [J]. IEEE/ACM Transactions on Networking, 1997, 5(5):601-615.
[10] Les Cottrell. Comparison of some Internet active end-to-end performance measurem ent Projects[R], http://www. Slac. Stanford.edu/comp/net/wan-mon /iep m-cf.html, 1999.
[11] Groschwitz N.K., Polyzos G.C.A time series model of long-term NSFNET backbone flow [J]. In: Proceedings of IEEE ICC, Pittsburgh, PA, 1994, 234-238.
[12] Sang A., Li S...Predictability analysis of network flow [J]. In: Proceedings of INFOCOM, TelAviv, Israel, 2000, 342-351.
[13]纪其进,董永强.基于小波域混合高斯模型的自相似流量合成算法[J].计算机研究与发展, 2006, 43(3):389-394.
[14]洪飞,吴智美.基于小波的多尺度网络流量预测模型[J].计算机学报, 2006, 29 (1):166-170.
[15]王新.自相似网络流量的建模与预测[D].北京:清华大学电子工程系, 2003.
[16]丛锁,韩良秀.基于离散小波变换的网络流量多重分形模型[J].通信学报, 2003, 24 (5):3-8.
[17]邹柏贤,刘强.基于ARMA模型的网络流量预测[J].计算机研究与发展, 2002, 39(12):1646-1652.
[18]邹柏贤,姚志强.一种网络流量平稳化方法[J].通信学报, 2004, 25(8):14-23.
[19]冯海亮,陈涤,林青家,等.一种基于神经网络的网络流量组合预测模型[J].计算机应用, 2006, 26(9):2206-2209.
[20]王建新,肖雪峰,高文宇.小时间粒度网络流量自回归预测分析[J].计算机工程与应用, 2005, 26(38):129-132.
[21]薛可,李增智,刘浏,等.基于ARIMA模型的网络流量预测[J].微电子与计算机, 2004, (4):182-186.
[22]李林峰,裘正定.时间序列分析在网络流量预测中的应用研究[A], 2005通信理论与技术新进展—第十届全国青年通信学术会议论文集[C], 2005, 234-236.
[23]胡申敏,许维胜,王中杰,等.基于分数差分和Fuzzy-AR的网络流量建模和预测[J].计算机工程与应用, 2006, (19):104-106.
[24]唐万梅.基于灰色支持向量机的新型预测模型[J].系统工程学报, 2006(4):411-413.
[25] Bor-Sen Chen,Sen-Chueh Peng and Ku-Chen Wang“,Traffic modeling,Prediction and congestion control for high-speed networks: A Fuzzy AR Approch”,IEEE Trans. On Fuzzy Sys., 2000,10.(8):491-508.
[26] Shie-Jue Lee,and Chun-Liang Hou,“A Neural-Fuzzy system for congestion control in ATM Networks”,IEEE Trans. Sys.,Man and Cybernetics-Part B:Cybernetics,2000,2(30):2-9.
[27] Huifang Feng and Yantai Shu, Study on Network Traffic Prediction Techniques[C]. Wireless Communications,Networking and Mobile Computing Proceedings,2005,vol(2):995-998.
[28] Y.shu,et al.,“Traffic Prediction Using FARIMA Models”,ICC’99,Vancouver, Canada,522-6,June6-10,1999.
[29] Michael Jiang, Analysis of Wireless Data Network Flow. http://www.ensc.sfu.cal people faculty/ljiljalcnl/presentations/michael/Michael_thesis/index.htm. 2002.
[30] S. F. Victor, M. Benjamin. Flow modeling for telecommunications networks [J]. IEEE communications magazine, 1994.
[31]邹柏贤,刘强.基于ARMA模型的网络流量预测[J].计算机研究与发2002,39 (12):1646-1652.
[32]蔡弘,陈惠民,李衍达.自相似业务模型--通信网络突发业务建模的新方法[J].通信学报, 1997,(11) .
[33]胡严,光照.重尾On/Off源模型生成自相似业务流研究[J].电路与系统学报, 2001,6(3):72-76.
[34] Qinghua Zhang and A.Benveniste,Wavelet Networks[J].IEEE Trans on Neural Networks,vol.3,no6,November1992.
[35] Abry P, Veitch D. Wavelet Analysis of Long-range Dependence Traffic[J].IEEE Trans. on Information Theory,1998,44(1):2-15.
[36] Tian Yangqin. Comparison of the Independent Wavelet Models to Network Traffic1[C].http://Proc. Of GLOBECOM’01. Piscataway, NJ, USA: IEEE Press, 2001: 1448-1452.
[37]金旗,裴昌幸,朱畅.ARIMA模型法分析网络流量[J].西安电子科技大学学报(自然科学版)2003,30(1).
[38]陈涛捷.灰色预测模型的一种拓广[J].系统工程,1990,8(4):50-52.
[39]李群.灰色预测模型的进一步拓广[J].系统工程理论与实践,1993,13(1):64-66.
[40]戴文战,李俊峰.基于函数x? a(a>0)变换的GM(1,l)模型及在我国农村人均住房面积建模中的应用[J].系统工程理论与实践,2004,24(11):63-67.
[41]李翠凤,戴文战.基于函数cot x变换的灰色建模方法[J].系统工程,2005,23 (3):110-114.
[42] Luo You-xin,Pen Zhu,Zhang Long-ting.Grey GM(l,1) model with function transfer method for the wear trend prediction and its application[J].Internal J of Plant Eng and Management,2001,21(4):220-232.
[43] Luo You-xin,Cai An-hui,Zhang Long-ting. Grey problems of mechanical transmission system in a reliability study[J].Internal J of Plant Eng and Management ,2001,21(2):104-110.
[44] Luo You-xin,Zhang Long-ting,Guo Hui-xin. Grey system judgement on reliability of mechanical equipment[J]. Internal J of Plant Eng and Manage ment ,2001,21(3):156-164.
[45]曹建华,刘渊,戴悦.基础残差改进的灰色模型网络流量预测[J].计算机工程与设计,2007,21(28):5133-5134.
[46]王耀南.智能信息处理技术[M].北京:高等教育出版社出版社, 2003.8: 67-69, 130-135.
[47] DE, Rumelhart, GE.Hinton Learning representations by back-propagation errors [J].Nature, 1986, 323:533-536.
[48] RA Jacobs.Increased rates of convergence through learning rate adaptation [J].Neural Networks, 1988, 1(4):295-308.
[49] Yuan Liu,Jianhua Cao. Network traffic prediction based on Grey Neural Network Integrated model[C].WiCOM '08. 4th International Conference,2008:1-4.
[50] Zhang Jun-fu, Deng Ben-rang. The Application of Fuzzy Mathematics [M]. Beijing: Geological Press1988, 209-213.
[51] Zhang Fuwei,Zhou Xuelian.Gray-Regression Variable Weight Combination Model for Load Forecasting[C]. International Conference on Risk Management and Engineering Management,2008,9:311-316.
[52] Jia Zhengyuan. Electricity consumption forecasting in peak load month based on variable weight combination forecasting model[C]. IEEE International Conference on Automation and Logistics, 2008,9:1265-1269.
[53]刘月卿,管德永.公路货运量变权组合预测模型研究[J].昆明理工大学学报,2007,4(32):53-55.
[54] A.Khotanzad and N.Sadek,“Multi-scale high-speed network traffic Prediction Using combination of neural networks”,Proceedings of the International Joint Conference on Neural Networks,2003,7(2):1071-1075.
[55] AlaxMa, Skitter: A tool for actively probing the Interne in order to analyze topology and performance[EB]:http://www.caida.org/tools/measurement/skitter.
[56] Govindan R, Tangmunarunkit H. , Heuristics for Internet Map Discovery [EB]. Ftp://ftp.use.edu/pub/csinfo/tech-reports/papers/99-717.ps.Z.
[57] Snifter Portable.www.atsweb.it/Images/Documenti/SNI_DS_Portable.pdf.
[58]杨建平,王峰.智能化网络性能分析与预测支撑系统设计[J].武汉大学学报. 2001 (2):75-78.
[59] McGregor, and H-W.Braun, and J.A.Borwn, The NLANR Network Analysis Infrastr ucture [J], IEEE Communications Magazine, 2000, 38(5):122-128.
[60] Claffy K, Monk TE, McRobb D. Internet tomography Nature[EB]. http://www.natur e.com/nature/webmatters/tomog/ tomog.html, 1999-01-07.
[61] Stephen Donnelly. High Precision Timing in Passive Measurements of Data Networ ks [D]. Hamilton, New Zealand. June 2002.
[62] Breitbart Y, Chan CY, Garofalakis M, Rastogi R, Silberschatz A. Efficiently monitoring bandwidth and latency in IP networks [J]. In: Proc. of the IEEE INFOCOM. Anchorage: IEEE, 2001.933-942.
[63]李学全,李春生.一种改进的模糊变权重组合预测方法[J].中南工业大学学报.2003,34(6):708-710.
[64]鄂加强,王耀南.一种新的非线性模糊自适应变权重组合预测模型[J].2006,20(4):123-126.
[2] Chen BS ,Pen SC, Wang KC. Flow modeling, prediction and congestion control for high-speed networks: A Fuzzy AR Approach [J]. IEEE Trans. On Fuzzy System, 2000, (8): 491-508.
[3] Mannersalo P. Gaussian and muhfractal processes in teletrattlc theory. PhD dissertation[EB].ESP0020003, V1T Publications 491, ISBN 951-6037–X (URL:http: //www.inf.vtt.inf/pdf/).
[4] Erramilli A, RouIghall M, Veitch D, Willinger W. Serf-similar traffic and network dynamics [J]. Proceedings of the IEEE.2002(5):90-96.
[5] Capp O, Moulines E. Long range dependence and heavy tail modeling for telegraphic data [J]. 2002(1):10-13.
[6] Wu G, Chong EKP, Givan R. Congestion control via online sampling. Proceedings of the 2001 IEEE Infocom Anchorage [J], AK.2001(4):1271-1280.
[7] Wang S, Xuan D, Bettati R, etal. Providing absolute differentiated services for real time application in static priority scheduling Networks [C]. Proceedings of the 2001 IEEE Infocom Anchorage, AK.2001.
[8] Feldman n A, Greenberg A, Lund C, etal. Netscop:traffic engineering for IP network [M]. IEEE Network Magazine.2000.
[9] Parson V. End-to-End routing behavior in the Internet [J]. IEEE/ACM Transactions on Networking, 1997, 5(5):601-615.
[10] Les Cottrell. Comparison of some Internet active end-to-end performance measurem ent Projects[R], http://www. Slac. Stanford.edu/comp/net/wan-mon /iep m-cf.html, 1999.
[11] Groschwitz N.K., Polyzos G.C.A time series model of long-term NSFNET backbone flow [J]. In: Proceedings of IEEE ICC, Pittsburgh, PA, 1994, 234-238.
[12] Sang A., Li S...Predictability analysis of network flow [J]. In: Proceedings of INFOCOM, TelAviv, Israel, 2000, 342-351.
[13]纪其进,董永强.基于小波域混合高斯模型的自相似流量合成算法[J].计算机研究与发展, 2006, 43(3):389-394.
[14]洪飞,吴智美.基于小波的多尺度网络流量预测模型[J].计算机学报, 2006, 29 (1):166-170.
[15]王新.自相似网络流量的建模与预测[D].北京:清华大学电子工程系, 2003.
[16]丛锁,韩良秀.基于离散小波变换的网络流量多重分形模型[J].通信学报, 2003, 24 (5):3-8.
[17]邹柏贤,刘强.基于ARMA模型的网络流量预测[J].计算机研究与发展, 2002, 39(12):1646-1652.
[18]邹柏贤,姚志强.一种网络流量平稳化方法[J].通信学报, 2004, 25(8):14-23.
[19]冯海亮,陈涤,林青家,等.一种基于神经网络的网络流量组合预测模型[J].计算机应用, 2006, 26(9):2206-2209.
[20]王建新,肖雪峰,高文宇.小时间粒度网络流量自回归预测分析[J].计算机工程与应用, 2005, 26(38):129-132.
[21]薛可,李增智,刘浏,等.基于ARIMA模型的网络流量预测[J].微电子与计算机, 2004, (4):182-186.
[22]李林峰,裘正定.时间序列分析在网络流量预测中的应用研究[A], 2005通信理论与技术新进展—第十届全国青年通信学术会议论文集[C], 2005, 234-236.
[23]胡申敏,许维胜,王中杰,等.基于分数差分和Fuzzy-AR的网络流量建模和预测[J].计算机工程与应用, 2006, (19):104-106.
[24]唐万梅.基于灰色支持向量机的新型预测模型[J].系统工程学报, 2006(4):411-413.
[25] Bor-Sen Chen,Sen-Chueh Peng and Ku-Chen Wang“,Traffic modeling,Prediction and congestion control for high-speed networks: A Fuzzy AR Approch”,IEEE Trans. On Fuzzy Sys., 2000,10.(8):491-508.
[26] Shie-Jue Lee,and Chun-Liang Hou,“A Neural-Fuzzy system for congestion control in ATM Networks”,IEEE Trans. Sys.,Man and Cybernetics-Part B:Cybernetics,2000,2(30):2-9.
[27] Huifang Feng and Yantai Shu, Study on Network Traffic Prediction Techniques[C]. Wireless Communications,Networking and Mobile Computing Proceedings,2005,vol(2):995-998.
[28] Y.shu,et al.,“Traffic Prediction Using FARIMA Models”,ICC’99,Vancouver, Canada,522-6,June6-10,1999.
[29] Michael Jiang, Analysis of Wireless Data Network Flow. http://www.ensc.sfu.cal people faculty/ljiljalcnl/presentations/michael/Michael_thesis/index.htm. 2002.
[30] S. F. Victor, M. Benjamin. Flow modeling for telecommunications networks [J]. IEEE communications magazine, 1994.
[31]邹柏贤,刘强.基于ARMA模型的网络流量预测[J].计算机研究与发2002,39 (12):1646-1652.
[32]蔡弘,陈惠民,李衍达.自相似业务模型--通信网络突发业务建模的新方法[J].通信学报, 1997,(11) .
[33]胡严,光照.重尾On/Off源模型生成自相似业务流研究[J].电路与系统学报, 2001,6(3):72-76.
[34] Qinghua Zhang and A.Benveniste,Wavelet Networks[J].IEEE Trans on Neural Networks,vol.3,no6,November1992.
[35] Abry P, Veitch D. Wavelet Analysis of Long-range Dependence Traffic[J].IEEE Trans. on Information Theory,1998,44(1):2-15.
[36] Tian Yangqin. Comparison of the Independent Wavelet Models to Network Traffic1[C].http://Proc. Of GLOBECOM’01. Piscataway, NJ, USA: IEEE Press, 2001: 1448-1452.
[37]金旗,裴昌幸,朱畅.ARIMA模型法分析网络流量[J].西安电子科技大学学报(自然科学版)2003,30(1).
[38]陈涛捷.灰色预测模型的一种拓广[J].系统工程,1990,8(4):50-52.
[39]李群.灰色预测模型的进一步拓广[J].系统工程理论与实践,1993,13(1):64-66.
[40]戴文战,李俊峰.基于函数x? a(a>0)变换的GM(1,l)模型及在我国农村人均住房面积建模中的应用[J].系统工程理论与实践,2004,24(11):63-67.
[41]李翠凤,戴文战.基于函数cot x变换的灰色建模方法[J].系统工程,2005,23 (3):110-114.
[42] Luo You-xin,Pen Zhu,Zhang Long-ting.Grey GM(l,1) model with function transfer method for the wear trend prediction and its application[J].Internal J of Plant Eng and Management,2001,21(4):220-232.
[43] Luo You-xin,Cai An-hui,Zhang Long-ting. Grey problems of mechanical transmission system in a reliability study[J].Internal J of Plant Eng and Management ,2001,21(2):104-110.
[44] Luo You-xin,Zhang Long-ting,Guo Hui-xin. Grey system judgement on reliability of mechanical equipment[J]. Internal J of Plant Eng and Manage ment ,2001,21(3):156-164.
[45]曹建华,刘渊,戴悦.基础残差改进的灰色模型网络流量预测[J].计算机工程与设计,2007,21(28):5133-5134.
[46]王耀南.智能信息处理技术[M].北京:高等教育出版社出版社, 2003.8: 67-69, 130-135.
[47] DE, Rumelhart, GE.Hinton Learning representations by back-propagation errors [J].Nature, 1986, 323:533-536.
[48] RA Jacobs.Increased rates of convergence through learning rate adaptation [J].Neural Networks, 1988, 1(4):295-308.
[49] Yuan Liu,Jianhua Cao. Network traffic prediction based on Grey Neural Network Integrated model[C].WiCOM '08. 4th International Conference,2008:1-4.
[50] Zhang Jun-fu, Deng Ben-rang. The Application of Fuzzy Mathematics [M]. Beijing: Geological Press1988, 209-213.
[51] Zhang Fuwei,Zhou Xuelian.Gray-Regression Variable Weight Combination Model for Load Forecasting[C]. International Conference on Risk Management and Engineering Management,2008,9:311-316.
[52] Jia Zhengyuan. Electricity consumption forecasting in peak load month based on variable weight combination forecasting model[C]. IEEE International Conference on Automation and Logistics, 2008,9:1265-1269.
[53]刘月卿,管德永.公路货运量变权组合预测模型研究[J].昆明理工大学学报,2007,4(32):53-55.
[54] A.Khotanzad and N.Sadek,“Multi-scale high-speed network traffic Prediction Using combination of neural networks”,Proceedings of the International Joint Conference on Neural Networks,2003,7(2):1071-1075.
[55] AlaxMa, Skitter: A tool for actively probing the Interne in order to analyze topology and performance[EB]:http://www.caida.org/tools/measurement/skitter.
[56] Govindan R, Tangmunarunkit H. , Heuristics for Internet Map Discovery [EB]. Ftp://ftp.use.edu/pub/csinfo/tech-reports/papers/99-717.ps.Z.
[57] Snifter Portable.www.atsweb.it/Images/Documenti/SNI_DS_Portable.pdf.
[58]杨建平,王峰.智能化网络性能分析与预测支撑系统设计[J].武汉大学学报. 2001 (2):75-78.
[59] McGregor, and H-W.Braun, and J.A.Borwn, The NLANR Network Analysis Infrastr ucture [J], IEEE Communications Magazine, 2000, 38(5):122-128.
[60] Claffy K, Monk TE, McRobb D. Internet tomography Nature[EB]. http://www.natur e.com/nature/webmatters/tomog/ tomog.html, 1999-01-07.
[61] Stephen Donnelly. High Precision Timing in Passive Measurements of Data Networ ks [D]. Hamilton, New Zealand. June 2002.
[62] Breitbart Y, Chan CY, Garofalakis M, Rastogi R, Silberschatz A. Efficiently monitoring bandwidth and latency in IP networks [J]. In: Proc. of the IEEE INFOCOM. Anchorage: IEEE, 2001.933-942.
[63]李学全,李春生.一种改进的模糊变权重组合预测方法[J].中南工业大学学报.2003,34(6):708-710.
[64]鄂加强,王耀南.一种新的非线性模糊自适应变权重组合预测模型[J].2006,20(4):123-126.