基于智能算法的网络流量预测技术研究
|
摘要
随着Internet的迅猛发展和更多的计算机联入Internet,互联网环境日趋复杂。为了实现资源共享的最终目标,网络传输数据量日益扩增,随之而带来的问题、故障层出不穷,给网络管理工作带来了沉重的负担。因此深入理解网络的行为特性和控制机制显得尤为重要。通过对网络流量的预测,了解网络之间的流量情况,以至对网络流量进行比较精确的分析和预测,十分有利于网络的设计和控制;通过设置路由功能,设计负载均衡,可以尽可能使拥塞带来的信息延迟和损耗程度降之最低;而且可以对网络进行入侵检测,发掘和排斥隐藏的攻击入侵行为。因此网络流量预测的可行性和必要性显得尤为重要,特别是高质量的预测对于管理和设计大规模网络环境意义重大。
本文研究的宗旨是为了提高网络流量的预测精度和稳定性,作者的工作是探索出新的网络预测模型。
第一,全面叙述了网络流量预测的背景、意义以及研究现状,为后续的研究工作奠定了基础;
第二,分析了网络流量的重要特性,包括自相似性、长相关性、多重分形特性等,这对掌握流量预测本质,对提高预测的精度有着重要的意义。
第三,在理解网络流量特性的基础上,分析了几种传统的网络流量模型,这对于用智能算法构造流量预测模型有着重要的指导意义;
第四,建立了基于小波包消噪和Elman网络的网络流量预测模型。针对传统Elman网络预测精度低,结合小波包消噪和Elman神经网络的优势,先将原始流量序列进行小波包消噪,将消噪后的序列作为Elman神经网络的输入,待预测序列作为输出。通过消噪后的前N天的流量序列,预测出后M天流量序列。
第五,提出一种新的网络流量预测模型,基于小波分析和AR-LSSVM理论,首先通过小波分析的方法对原始序列进行小波分解,再进行单支重构操作,利用最小二乘支持向量机和自回归模型分别预测,最后再一次进行重构操作,最终实现原始序列的预测结果,提高了网络流量的预测精度以及稳定性。
第六,建立了基于QPSO优化BP的网络流量预测模型。针对PSO算法的缺点,采用QPSO算法对BP神经网络的权值和阈值进行优化,并利用历史记录训练BP网络。
With the rapid development and more computers linked into the Internet network, the scale of internet is becoming more complicated, in order to realize the goal of resource share, the amount of the network traffic is increasing, the task and stress of network management becomes heavily. And failures and questions appear again and again, it is very important to comprehend the control mechanism and complicated behavioral character. It has important significance through analysis and predictions: It contributes to understand situation, so the network traffic can be accurately predicted and simulated. It’s useful for designing and controlling. It can be more effective for optimization, and be better for routing design and load-balanced design. It could determine the network congestion control, which can reduce network congestion due to the loss and delay of information. It can make full use of network resources to improve service quality. It may realize intrusion detection, detect and exclue potential attacks and intrusions. Network traffic prediction is necessary,high quality traffic prediction has significant meanings for large scale network management and design.
Purpose of the study is to improve the forecast accuracy and stability of network traffic,the main work is to research and explore new network prediction models.
Firstly, in the paper background, significance and research status about network traffic prediction are comprehensively narrated, to make foundation for the following researches.
Secondly, the paper analyzes some important characters, including self-similarity, long-range dependence, multifarious characteristics. It’s important for mastering traffic prediction essence and improving traffic accuracy.
Thirdly,Based on understanding the characteristics about network traffic, several traditional network traffic models are analyzed, which has significant guide meanings for making use of intelligent algorithms for traffic prediction model construction
Fourthly, a model based on wavelet packet de-noising and Elman is found.De-noising the traffic series with wavelet packet, then taking the de-noised series as the input of Elman while the predictive series as the output of Elman. By using the N days’de-noised traffic series to forecast the later M days’predictive series. The N days’de-noised series is token as a sliding window and mapped into the later M days’predictive series.
Fifthly, a mode based on wavelet analysis and AR-LSSVM is established. Firstly, the series are decomposed, getting a low frequency signal and several high frequency signals, the approximation part and detail parts were reconstructed to the original level, the next sequence of each were predicted using least squares support vector machines and self-regression model, the final, with the various reconstructed sequence, getting the prediction sequence of original sequence, improving the forecast accuracy and stability of network traffic.
Sixthly, a mode based on BPNN optimized by QPSO algorithm is established. It considers the flaw of PSO algorithm.QPSO algorithm is applied to optimize the weights and thresholds in BP neural network,and historical records are used to train BP neural network.
本文研究的宗旨是为了提高网络流量的预测精度和稳定性,作者的工作是探索出新的网络预测模型。
第一,全面叙述了网络流量预测的背景、意义以及研究现状,为后续的研究工作奠定了基础;
第二,分析了网络流量的重要特性,包括自相似性、长相关性、多重分形特性等,这对掌握流量预测本质,对提高预测的精度有着重要的意义。
第三,在理解网络流量特性的基础上,分析了几种传统的网络流量模型,这对于用智能算法构造流量预测模型有着重要的指导意义;
第四,建立了基于小波包消噪和Elman网络的网络流量预测模型。针对传统Elman网络预测精度低,结合小波包消噪和Elman神经网络的优势,先将原始流量序列进行小波包消噪,将消噪后的序列作为Elman神经网络的输入,待预测序列作为输出。通过消噪后的前N天的流量序列,预测出后M天流量序列。
第五,提出一种新的网络流量预测模型,基于小波分析和AR-LSSVM理论,首先通过小波分析的方法对原始序列进行小波分解,再进行单支重构操作,利用最小二乘支持向量机和自回归模型分别预测,最后再一次进行重构操作,最终实现原始序列的预测结果,提高了网络流量的预测精度以及稳定性。
第六,建立了基于QPSO优化BP的网络流量预测模型。针对PSO算法的缺点,采用QPSO算法对BP神经网络的权值和阈值进行优化,并利用历史记录训练BP网络。
With the rapid development and more computers linked into the Internet network, the scale of internet is becoming more complicated, in order to realize the goal of resource share, the amount of the network traffic is increasing, the task and stress of network management becomes heavily. And failures and questions appear again and again, it is very important to comprehend the control mechanism and complicated behavioral character. It has important significance through analysis and predictions: It contributes to understand situation, so the network traffic can be accurately predicted and simulated. It’s useful for designing and controlling. It can be more effective for optimization, and be better for routing design and load-balanced design. It could determine the network congestion control, which can reduce network congestion due to the loss and delay of information. It can make full use of network resources to improve service quality. It may realize intrusion detection, detect and exclue potential attacks and intrusions. Network traffic prediction is necessary,high quality traffic prediction has significant meanings for large scale network management and design.
Purpose of the study is to improve the forecast accuracy and stability of network traffic,the main work is to research and explore new network prediction models.
Firstly, in the paper background, significance and research status about network traffic prediction are comprehensively narrated, to make foundation for the following researches.
Secondly, the paper analyzes some important characters, including self-similarity, long-range dependence, multifarious characteristics. It’s important for mastering traffic prediction essence and improving traffic accuracy.
Thirdly,Based on understanding the characteristics about network traffic, several traditional network traffic models are analyzed, which has significant guide meanings for making use of intelligent algorithms for traffic prediction model construction
Fourthly, a model based on wavelet packet de-noising and Elman is found.De-noising the traffic series with wavelet packet, then taking the de-noised series as the input of Elman while the predictive series as the output of Elman. By using the N days’de-noised traffic series to forecast the later M days’predictive series. The N days’de-noised series is token as a sliding window and mapped into the later M days’predictive series.
Fifthly, a mode based on wavelet analysis and AR-LSSVM is established. Firstly, the series are decomposed, getting a low frequency signal and several high frequency signals, the approximation part and detail parts were reconstructed to the original level, the next sequence of each were predicted using least squares support vector machines and self-regression model, the final, with the various reconstructed sequence, getting the prediction sequence of original sequence, improving the forecast accuracy and stability of network traffic.
Sixthly, a mode based on BPNN optimized by QPSO algorithm is established. It considers the flaw of PSO algorithm.QPSO algorithm is applied to optimize the weights and thresholds in BP neural network,and historical records are used to train BP neural network.
引文
1. Mannersalo P. Gaussian and muhfractal proeesses in teletrattlc Theory. PhD dissertation. ESP002003, VIT Publications 491, ISBN 951-6037-X (URL:http://www.inf.vtt.inf/pdf/)
2. Erramilli A,Roulghall M,VeitehD,Willinger W.Serf-similar traffic and network dynamics.Proceedings of the IEEE.2002(5):90-96
3. Capp O,Moulines E.Long range dependence and heavy tail modeling for telegraphic data.2002(1):10-13
4. Wu G,Chong E K P,Givan R.Congestion control via online sampling.Proeeedings of the 2001 IEEE Infocom Anchorage,AK.2001(4):1271-1280
5.冯海亮.基于联合神经网络的流量预测模型[D]:[硕士学位论文].山东:山东大学,2007
6. Fuchs E,Jackson P E.Estimates of Distribtion of Random Variables for Certain Computer Communication Traffic Models[J].Communication of ACM,1970,13(12):752-767
7.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(12): 1645-1652
8.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
9.薛可,李增智,刘浏,宋承谦.基于ARIMA模型的网络流量预测[J].微电子学与计算机.2004,21(7):84-87
10.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[J].通信学报.2005,26(3):136-140
11.韩良秀,丛锁等.基于小波技术的网络流量特性刻画[J].小型微型计算机系统,2001,22(9):1116-1118
12.丛锁,韩良秀等.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):43-48
13.何建.基于时间序列的网络流量分析与预测[J].中国科技信息,2005(22):8-10
14.雷霆,余镇危.一种网络流量预测的小波神经网络模型[J].计算机应用,2006,26(3): 526-528
15. Sun J., Xu W. B. A global search strategy of quantum—behaved particle swarm optimization[C] Preceedings of IEEE confereuce on Cybernetics and Intelligent Systems,2004:111-116
16. Cruz R L.A Calculus for Network Delay,Part I:Network Elements in Isolation[J].IEEE Trans on Information Theory,1991,37(1):114-131
17. Cruz R L.A Calculus for Network Delay,Part II:Network Analysis[J].IEEE Trans on Information Theory,1991,37(1):132-141
18. Kantz H.非线性时间序列分析[M].北京:清华大学出版,2002
19. Paxson V,Floyd S.Wide Area Traffic:The Failure of Poisson Modeling,Prediction,and Congestion Control for High-speed Networks:A Fuzzy AR Approach[J].IEEE Transaction on Fuzzy Systems,2000,8(5):491-506
20. Vapnik V N. Statistical Learning Theory[M].New York:New York Wiley,1998.
21. J.A.K.Suykens,J.Vandewalle.Least squares support vector machine classifiers[J].Neural Processing Letters(S1370-4621),1999,9(3):293-300
22.胡大民.网络流量自相似特性与预测研究[D]:[硕士学位论文].浙江:浙江大学,2008
23. P.Abry.Multiscale Nature of Network Traffic[J].IEEE Signal Processing Magazine.2002,1 9(3):28-46;T.Karagiannis,M.Faloutsos,R.Riedi.Long-range Dependence:Now You See It,NowYou Don’t.IEEE GLOBECOM’02.2002
24.王风宇,云晓春,申伟东.基于小波变换的网络流量在线预测模型[J].高技术通讯.2006(12):1220-1225
25.洪飞,吴志美.基于小波的多尺度网络流量预测模型[J].计算机学报.2006(1):167-169
26.陈惠民,蔡弘,李衍达.自相似业务:基于多分辨率采样和小波分析的Hurst参数估计方法[J].电子学报,1998,26(7):88-93
27. Paxson V.,Floyd S..Wide area traffic:the failure of possion model[J].IEEE/ACM Trans on Networking.1995,3(3):226-244
28. Leland W S,Taqqu M,Willinger W,et all. On the self-similar nature of Ethernet traffic(extended version).IEEE/ACM Trans.Networking.1994(1):1-15
29. Erramilli A.,Willinger W.and Wang J.L.,Modeling and Management of Self-Similar Traffic Flows in High-Speed Networks[J].Network System Design,Gordon and Breach Science Publishers,1999
30. Flandrin P.Wavelet Analysis and Synthesis of Fractional Brownian Motion[J].IEEE Transactions on Information Theory,Vol.38,No.2,March 1992
31.谭晓玲,梅成刚,刘兰.网络业务流的自相似特性研究[J].现代计算机,2005,8
32.邬源杨,董玮文,杨宇航.自相似网络流量的长相关分析方法[J].计算机工程,2003.05(1000~3428)
33.冯怀成.网络流量的单分形和多分形特性研究[J].信息科技,2007,3:89-90
34.王西锋,高岭,张晓孪.自相似网络流量预测的分析和研究[J].计算机技术与发展,2007,17(11):42-45
35.刘华阳.网络系统仿真中的流量模型研究[J].学术论文,2006.02:(1009-8119)
36.陈云龙,叶梧,冯穗力等.网络流量建模的物理解读[J].科学技术与工程,2006,05:(1671~1815)
37.王燕.应用时间序列[M].北京:中国人民大学出版社,2005
38.刘杰,黄亚楼.BP神经网络的非线性网络流量预测[J].计算机应用,2007,27(7):1770-1772
39.郭计云,王福明.基于小波包变换的信号去噪方法研究[J].现代电子技术,2007,258(19):55-50
40.曲国庆,党亚民,章传银,苏晓庆.小波包消噪方法分析及改进[J].大地测量与地球动力学,2008,28(4):102-106
41.李志兴,谢向荣,梁述海,小波包降消噪在液压泵故障诊断中的应用[J].船海工程,2006,38-41
42.王俊松.基于Elman神经网络的网络流量建模及预测[J].计算机工程,2009,35(9):190-191
43.郭长河,1,郭晗,2,范杰.运用Elman神经网络的邯郸市人才需求预测[J].河北工程大学学报(社会科学版),2008,25(3):26-28
44.王艳姣,邓自旺,王耀庭,宋德众.基于BP和Elman神经网络的福建省汛期旱涝预测模型[J].南京气象学院学报.2004,27(6):776-783
45.余健,郭平.,基于改进的Elman神经网络的股价预测模型[J].计算机技术与发展,2008,18(3):43-45
46.余健,郭平,基于改进小波神经网络的网络流量预测研究[A],计算机应用,1001-9081(2007)12-2968-03
47.飞思科技产品研发中心.小波分析理论与实现[M].北京:电子工业出版社,2005
48. Hopfield J, Tank D. 'Neural' Computation of Decisions in Optimization Problems[C]. Biological Cybernetics 1985, 52:141-1528
49.胡俊,胡玉清,肖中卿.基于小波变换的网络流量预测模型[J],计算机工程,2008,34(19):112-114
50. Yu I,Kim C. A Novel Short-Term Load Forecasting Technique Using Wavelet Transform Analysis[J].Electric machines and power systems,2000,28:537:549.
51. Nektarios Moraitis.ANN Prediction Models for Outdoor SIMO Millimeter Band System[A].Artificial intelligence and innovations 2007 :[C].2007.
52.刘杰,黄亚楼.基于BP神经网络的非线性网络流量预测[J],计算机应用,2007,27(7):1770-1772.
53. VapnikV N.The nature of statistical learning theory[M].2nded.New York:Springer—Verlag,1999.
54. Xiaodong Wang,Haoran Zhang,Changjiang Zhang(等),Prediction of Chaotic Time Series Using LS-SVM with Automatic Parameter Selection.[c]Proceedings of the Sixth International Conference on Parallel and Distributed Computing,Applications and Technologies.2005,pp:
55. Haishan Wu,Xiaoling Chang.Power Load Forecasting with Least Squares Support Vector Machines and Chaos Theory[c]Intelligent Control and Automation, 2006. WCICA 2006. The Sixth World Congress on Volume 1, 2006 Page(s):4369 - 4373 .
56. Wen Guo,Yizheng Qiao,Haiyan Hou.BP neural network optimized with PSO algorithm and its application in forecasting. Proceedings of the IEEE international Conference on Information Acquisition. 2006:617-621.
57. WEI SUN,YING ZOU.Short Term Load Forecasting Based on BP Neural Network Trained by PSO[C].Proceedings of the Sixth International Conference on Machine Learning and Cybernetics,Hong Kong,19-22 August 2007:2863-2866.
58. J. Sun, B. Feng, W.B Xu. Particle Swarm Optimization with Particles Having Quantum Behavior[C]. Proc. 2004 Congress on Evolutionary Computation, 325-331
59.赵振江.基于PSO-BP神经网络的网络流量预测与研究[J].计算机应用与软件2009,26(1): 218-221
60. Jun Sun,Wenbo Xu,Bin Feng.Adaptive Parameter Control for Quantum-behaved ParticleSwarm Optimization on Individual Level[J].Systems,Man and Cybernetics,IEEE International Conference ,2005,4(10-12):3049-3054
61.张春燕,须文波,孙俊等.MQPSO:一种具有多群体与多阶段的QPSO算法[J].计算机应用研究,2007,24(3):100-102
62. Sun J., Xu W. B. A global search strategy of quantum—behaved particle swarm optimization[C] Preceedings of IEEE confereuce on Cybernetics and Intelligent Systems,2004:111-116
63.王鹏,刘渊.基于改进的QPSO训练BP网络的网络流量预测[J].计算机应用研究,2009,26(1):229-301
64.冯海亮,林青家,陈涤等.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):2206-2208
65. Kennedy J,Eberhart R.Partical swarm optimization.Proceedings of the IEEE International Conference on Neural Network,Perth,Australia,IEEE Service Center,Piscataway,N,J,1995,4:1942-1948
66. Clerc M,Kennedy J.The partical swarm-explosion,stability and convergence in a multidimensional complex space.IEEE Trans on Evolutionary Computation,2002,6(1):58-73
67. Shi Y,Eberhart R C.Empirical study of particle wwarm optimization.Proceeding of the 1999 Congress on Evolutionary Computation-CEC99(Cat No 99TH8086),1999,3:1945-1950
68. Eberhart R C, Shi YComparing inertia weights and constriction factors in particle swarm optimization.Proceedings of the 2000 Congress on Evlutionary Computation.CEC00(Cat No 00TH8512),2000,1:84-88
69. Hu X H,Eberhart R C,Shi Y H.Engineering optimization with particle swarm Proceedings of the 2003 IEEE Swarm Inteligence Symposium(SIS 03),2003:53-57
70. Angeline P J.Using selection to improve particle swarm optimization.IEEE International Conference on Evolutionary Computation-Proceedings,1998:84-89
71. Ozcan E,Mohan C K,Particle swarm optimization:surfing the waves.Proceedings of the Congress on Evolutionary Computation-CEC99(Cat NO 99TH8406),1999,3:1939-1944
72. Y. Jin, M. Olhofer, Sendhoff B.Dynamic weighted Aggregation for Evolutionary Multi-Objective Optimization: Why Does It Work and How[C] In: Proceedings GECCO2001 Conference 2001
2. Erramilli A,Roulghall M,VeitehD,Willinger W.Serf-similar traffic and network dynamics.Proceedings of the IEEE.2002(5):90-96
3. Capp O,Moulines E.Long range dependence and heavy tail modeling for telegraphic data.2002(1):10-13
4. Wu G,Chong E K P,Givan R.Congestion control via online sampling.Proeeedings of the 2001 IEEE Infocom Anchorage,AK.2001(4):1271-1280
5.冯海亮.基于联合神经网络的流量预测模型[D]:[硕士学位论文].山东:山东大学,2007
6. Fuchs E,Jackson P E.Estimates of Distribtion of Random Variables for Certain Computer Communication Traffic Models[J].Communication of ACM,1970,13(12):752-767
7.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(12): 1645-1652
8.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
9.薛可,李增智,刘浏,宋承谦.基于ARIMA模型的网络流量预测[J].微电子学与计算机.2004,21(7):84-87
10.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[J].通信学报.2005,26(3):136-140
11.韩良秀,丛锁等.基于小波技术的网络流量特性刻画[J].小型微型计算机系统,2001,22(9):1116-1118
12.丛锁,韩良秀等.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):43-48
13.何建.基于时间序列的网络流量分析与预测[J].中国科技信息,2005(22):8-10
14.雷霆,余镇危.一种网络流量预测的小波神经网络模型[J].计算机应用,2006,26(3): 526-528
15. Sun J., Xu W. B. A global search strategy of quantum—behaved particle swarm optimization[C] Preceedings of IEEE confereuce on Cybernetics and Intelligent Systems,2004:111-116
16. Cruz R L.A Calculus for Network Delay,Part I:Network Elements in Isolation[J].IEEE Trans on Information Theory,1991,37(1):114-131
17. Cruz R L.A Calculus for Network Delay,Part II:Network Analysis[J].IEEE Trans on Information Theory,1991,37(1):132-141
18. Kantz H.非线性时间序列分析[M].北京:清华大学出版,2002
19. Paxson V,Floyd S.Wide Area Traffic:The Failure of Poisson Modeling,Prediction,and Congestion Control for High-speed Networks:A Fuzzy AR Approach[J].IEEE Transaction on Fuzzy Systems,2000,8(5):491-506
20. Vapnik V N. Statistical Learning Theory[M].New York:New York Wiley,1998.
21. J.A.K.Suykens,J.Vandewalle.Least squares support vector machine classifiers[J].Neural Processing Letters(S1370-4621),1999,9(3):293-300
22.胡大民.网络流量自相似特性与预测研究[D]:[硕士学位论文].浙江:浙江大学,2008
23. P.Abry.Multiscale Nature of Network Traffic[J].IEEE Signal Processing Magazine.2002,1 9(3):28-46;T.Karagiannis,M.Faloutsos,R.Riedi.Long-range Dependence:Now You See It,NowYou Don’t.IEEE GLOBECOM’02.2002
24.王风宇,云晓春,申伟东.基于小波变换的网络流量在线预测模型[J].高技术通讯.2006(12):1220-1225
25.洪飞,吴志美.基于小波的多尺度网络流量预测模型[J].计算机学报.2006(1):167-169
26.陈惠民,蔡弘,李衍达.自相似业务:基于多分辨率采样和小波分析的Hurst参数估计方法[J].电子学报,1998,26(7):88-93
27. Paxson V.,Floyd S..Wide area traffic:the failure of possion model[J].IEEE/ACM Trans on Networking.1995,3(3):226-244
28. Leland W S,Taqqu M,Willinger W,et all. On the self-similar nature of Ethernet traffic(extended version).IEEE/ACM Trans.Networking.1994(1):1-15
29. Erramilli A.,Willinger W.and Wang J.L.,Modeling and Management of Self-Similar Traffic Flows in High-Speed Networks[J].Network System Design,Gordon and Breach Science Publishers,1999
30. Flandrin P.Wavelet Analysis and Synthesis of Fractional Brownian Motion[J].IEEE Transactions on Information Theory,Vol.38,No.2,March 1992
31.谭晓玲,梅成刚,刘兰.网络业务流的自相似特性研究[J].现代计算机,2005,8
32.邬源杨,董玮文,杨宇航.自相似网络流量的长相关分析方法[J].计算机工程,2003.05(1000~3428)
33.冯怀成.网络流量的单分形和多分形特性研究[J].信息科技,2007,3:89-90
34.王西锋,高岭,张晓孪.自相似网络流量预测的分析和研究[J].计算机技术与发展,2007,17(11):42-45
35.刘华阳.网络系统仿真中的流量模型研究[J].学术论文,2006.02:(1009-8119)
36.陈云龙,叶梧,冯穗力等.网络流量建模的物理解读[J].科学技术与工程,2006,05:(1671~1815)
37.王燕.应用时间序列[M].北京:中国人民大学出版社,2005
38.刘杰,黄亚楼.BP神经网络的非线性网络流量预测[J].计算机应用,2007,27(7):1770-1772
39.郭计云,王福明.基于小波包变换的信号去噪方法研究[J].现代电子技术,2007,258(19):55-50
40.曲国庆,党亚民,章传银,苏晓庆.小波包消噪方法分析及改进[J].大地测量与地球动力学,2008,28(4):102-106
41.李志兴,谢向荣,梁述海,小波包降消噪在液压泵故障诊断中的应用[J].船海工程,2006,38-41
42.王俊松.基于Elman神经网络的网络流量建模及预测[J].计算机工程,2009,35(9):190-191
43.郭长河,1,郭晗,2,范杰.运用Elman神经网络的邯郸市人才需求预测[J].河北工程大学学报(社会科学版),2008,25(3):26-28
44.王艳姣,邓自旺,王耀庭,宋德众.基于BP和Elman神经网络的福建省汛期旱涝预测模型[J].南京气象学院学报.2004,27(6):776-783
45.余健,郭平.,基于改进的Elman神经网络的股价预测模型[J].计算机技术与发展,2008,18(3):43-45
46.余健,郭平,基于改进小波神经网络的网络流量预测研究[A],计算机应用,1001-9081(2007)12-2968-03
47.飞思科技产品研发中心.小波分析理论与实现[M].北京:电子工业出版社,2005
48. Hopfield J, Tank D. 'Neural' Computation of Decisions in Optimization Problems[C]. Biological Cybernetics 1985, 52:141-1528
49.胡俊,胡玉清,肖中卿.基于小波变换的网络流量预测模型[J],计算机工程,2008,34(19):112-114
50. Yu I,Kim C. A Novel Short-Term Load Forecasting Technique Using Wavelet Transform Analysis[J].Electric machines and power systems,2000,28:537:549.
51. Nektarios Moraitis.ANN Prediction Models for Outdoor SIMO Millimeter Band System[A].Artificial intelligence and innovations 2007 :[C].2007.
52.刘杰,黄亚楼.基于BP神经网络的非线性网络流量预测[J],计算机应用,2007,27(7):1770-1772.
53. VapnikV N.The nature of statistical learning theory[M].2nded.New York:Springer—Verlag,1999.
54. Xiaodong Wang,Haoran Zhang,Changjiang Zhang(等),Prediction of Chaotic Time Series Using LS-SVM with Automatic Parameter Selection.[c]Proceedings of the Sixth International Conference on Parallel and Distributed Computing,Applications and Technologies.2005,pp:
55. Haishan Wu,Xiaoling Chang.Power Load Forecasting with Least Squares Support Vector Machines and Chaos Theory[c]Intelligent Control and Automation, 2006. WCICA 2006. The Sixth World Congress on Volume 1, 2006 Page(s):4369 - 4373 .
56. Wen Guo,Yizheng Qiao,Haiyan Hou.BP neural network optimized with PSO algorithm and its application in forecasting. Proceedings of the IEEE international Conference on Information Acquisition. 2006:617-621.
57. WEI SUN,YING ZOU.Short Term Load Forecasting Based on BP Neural Network Trained by PSO[C].Proceedings of the Sixth International Conference on Machine Learning and Cybernetics,Hong Kong,19-22 August 2007:2863-2866.
58. J. Sun, B. Feng, W.B Xu. Particle Swarm Optimization with Particles Having Quantum Behavior[C]. Proc. 2004 Congress on Evolutionary Computation, 325-331
59.赵振江.基于PSO-BP神经网络的网络流量预测与研究[J].计算机应用与软件2009,26(1): 218-221
60. Jun Sun,Wenbo Xu,Bin Feng.Adaptive Parameter Control for Quantum-behaved ParticleSwarm Optimization on Individual Level[J].Systems,Man and Cybernetics,IEEE International Conference ,2005,4(10-12):3049-3054
61.张春燕,须文波,孙俊等.MQPSO:一种具有多群体与多阶段的QPSO算法[J].计算机应用研究,2007,24(3):100-102
62. Sun J., Xu W. B. A global search strategy of quantum—behaved particle swarm optimization[C] Preceedings of IEEE confereuce on Cybernetics and Intelligent Systems,2004:111-116
63.王鹏,刘渊.基于改进的QPSO训练BP网络的网络流量预测[J].计算机应用研究,2009,26(1):229-301
64.冯海亮,林青家,陈涤等.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):2206-2208
65. Kennedy J,Eberhart R.Partical swarm optimization.Proceedings of the IEEE International Conference on Neural Network,Perth,Australia,IEEE Service Center,Piscataway,N,J,1995,4:1942-1948
66. Clerc M,Kennedy J.The partical swarm-explosion,stability and convergence in a multidimensional complex space.IEEE Trans on Evolutionary Computation,2002,6(1):58-73
67. Shi Y,Eberhart R C.Empirical study of particle wwarm optimization.Proceeding of the 1999 Congress on Evolutionary Computation-CEC99(Cat No 99TH8086),1999,3:1945-1950
68. Eberhart R C, Shi YComparing inertia weights and constriction factors in particle swarm optimization.Proceedings of the 2000 Congress on Evlutionary Computation.CEC00(Cat No 00TH8512),2000,1:84-88
69. Hu X H,Eberhart R C,Shi Y H.Engineering optimization with particle swarm Proceedings of the 2003 IEEE Swarm Inteligence Symposium(SIS 03),2003:53-57
70. Angeline P J.Using selection to improve particle swarm optimization.IEEE International Conference on Evolutionary Computation-Proceedings,1998:84-89
71. Ozcan E,Mohan C K,Particle swarm optimization:surfing the waves.Proceedings of the Congress on Evolutionary Computation-CEC99(Cat NO 99TH8406),1999,3:1939-1944
72. Y. Jin, M. Olhofer, Sendhoff B.Dynamic weighted Aggregation for Evolutionary Multi-Objective Optimization: Why Does It Work and How[C] In: Proceedings GECCO2001 Conference 2001