互联网传播行为的时序演化与预测

doi:10.11959/j.issn.1000-436x.2018096

通信学报 ›› 2018, Vol. 39 ›› Issue (6): 116-126.doi: 10.11959/j.issn.1000-436x.2018096

互联网传播行为的时序演化与预测

田鹤¹,赵海²,王进法²,林川²

¹ 辽宁科技学院工程实践中心，辽宁本溪 117004
² 东北大学计算机科学与工程学院，辽宁沈阳 110004

修回日期:2018-04-02 出版日期:2018-06-01 发布日期:2018-07-09
作者简介:田鹤（1985-），女，辽宁沈阳人，辽宁科技学院讲师，主要研究方向为计算机网络、复杂网络。|赵海（1959-），男，辽宁沈阳人，博士，东北大学教授、博士生导师，主要研究方向为复杂网络、嵌入式系统、普适计算等。|王进法（1988-），男，山东德州人，东北大学博士生，主要研究方向为互联网拓扑分析、数据融合。|林川（1988-），男，辽宁凤城人，东北大学博士生，主要研究方向为复杂网络、软件定义网络。
基金资助:
国家自然科学基金资助项目(60973022)

Timing evolution and prediction of Internet transmission behavior

He TIAN¹,Hai ZHAO²,Jinfa WANG²,Chuan LIN²

¹ Engineering Practice Center,Liaoning Institute of Science and Technology,Benxi 117004,China
² School of Computer Science and Engineering,Northeastern University,Shenyang 110004,China

Revised:2018-04-02 Online:2018-06-01 Published:2018-07-09
Supported by:
The National Natural Science Foundation of China(60973022)

摘要/Abstract

摘要：

互联网的传播行为对研究网络拓扑结构和动态行为的关系具有重要作用。选取CAIDA_Ark项目下不同地区4个监测点的有效路径样本数据，统计网络访问时间与访问直径，发现它们的相关性极弱，网络访问时间呈多峰重尾分布。采用非线性时间序列分析方法对网络访问时间演化序列混沌辨析，结果表明其时序演化具有混沌特征。在此基础上，引入 Logistic 方程建立网络传播行为预测模型，并用粒子群优化算法对模型参数取优，用 4个监测点的网络访问时间序列对模型进行实验，从准确性和可用性这2个方面对模型进行评价，结果表明，短期内该模型能够对网络传播行为做出准确预测，在一段时期内，可作为网络行为演化预测的工具。

关键词: 互联网传播, 网络访问时间, Logistic模型, 混沌特征, 行为预测

Abstract:

The transmission behavior of Internet plays an importance role in the research on the relationship between network topology structure and dynamic behavior.Selecting effective path samples in four monitoring points which from different regions authorized by CAIDA_Ark project and statistics network traveling time and traveling diameter,their correlation is very weak,network traveling time is presented on multi-peak and heavy tail distribution.Using nonlinear time sequences analysis method to identify the Chaos characteristics of network traveling time evolution sequences.The results show that their timing evolution has Chaos characteristics.Based on this,the Logistic equation was lead to establish network transmission behavior prediction model,and particle swarm optimization (PSO) was used to optimize model parameters.The model by the network traveling time sequences of four monitoring points was experimented,evaluated it from accuracy and availability,the results show that the model can predict network transmission behavior accurately in the short term.It can be used as a tool for predicting the network behaviors’ evolution in a period of time.

Key words: Internet transmission, network traveling time, Logistic model, Chaos characteristics, behavior prediction

中图分类号:

TP393.6

田鹤,赵海,王进法,林川. 互联网传播行为的时序演化与预测[J]. 通信学报, 2018, 39(6): 116-126.

He TIAN,Hai ZHAO,Jinfa WANG,Chuan LIN. Timing evolution and prediction of Internet transmission behavior[J]. Journal on Communications, 2018, 39(6): 116-126.

图/表 13

表1

图1

表2

图2

图3

表3

图4

图5

图6

图7

图8

表4

图9

参考文献 19

[1]	YOOK S H , JEONG H , BARABASI A L . Modeling the Internet’s large-scale topology[J]. Proceedings of the National Academy of Sciences, 2002,99(21): 13382-13386.
[2]	PASTOR-SATORRAS R , VESPIGNANI A . Evolution and structure of the Internet:a statistical physics approach[M]. Cambridge: Cambridge University Press, 2007.
[3]	KROGFOSS B , WELDON M , SOFMAN L . Internet architecture evolution and the complex economies of content peering[J]. Bell Labs Technical Journal, 2012,17(1): 163-184.
[4]	DING W , YAN Z , DENG R H . A survey on future Internet security architectures[J]. IEEE Access, 2016,4: 4374-4393.
[5]	除久强, 王进法, 张君 ,等. 基于度相关性病毒传播模型及其分析[J]. 中国科学:信息科学, 2014,44(6): 793-810.
	XU J Q , WANG J F , ZHANG J ,et al. Virus spreading model based on degree correlation and its analysis[J]. Scientia Sinica Informations, 2014,44(6): 793-810.
[6]	ZHANG S , ZHAO H . Community identification in networks with unbalanced structure[J]. Physical Review E, 2012,337(6092): 337-341.
[7]	WANG P , AKYILDIZ I F . Improving network connectivity in the presence of heavy-tailed interference[J]. IEEE Transactions on Wireless Communications, 2014,13(10): 5427-5439.
[8]	徐野, 赵海, 苏威积 ,等. Internet 网络的访问直径分析[J]. 计算机学报, 2006,5(29): 690-698.
	XU Y , ZHAO H , SU W J ,et al. Analysis on traveling diameter of Internet[J]. Chinese Journal of Computers, 2006,5(29): 690-698.
[9]	隋岩, 曹飞 . 从混沌理论认识互联网群体传播特性[J]. 学术界, 2013(2): 86-94.
	SU Y , CAO F . Study on features of Internet group communication by chaos theory[J]. Condensed Paper, 2013(2): 86-94.
[10]	YE Z , MISTRY S , BOUGUETTAYA A ,et al. Long-term QoS-aware cloud service composition using multivariate time series analysis[J]. IEEE Transactions on Services Computing, 2016,9(3): 1.
[11]	CHAI S H , LIM J S . Forecasting business cycle with chaotic time series based on neural network with weighted fuzzy membership functions[J]. Chaos Solitons ＆ Fractals, 2016,90: 118-126.
[12]	林川, 赵海, 毕远国 ,等. 互联网网络时延特征研究[J]. 通信学报, 2015,36(3): 163-174.
	LIN C , ZHAO H , BI Y G ,et al. Research on network delay of Internet[J]. Journal on Communications, 2015,36(3): 163-174.
[13]	HUFFAKER B , FOMENKOV M , PLUMMER D J ,et al. Distance metrics in the Internet[J]. IEEE International Telecommunications Symposium, 2002: 200-202.
[14]	王光义, 袁方 . 级联混沌及其动力学特性研究[J]. 物理学报, 2013,62(2): 020506.
	WANG G Y , YUAN F . Cascade Chaos and its dynamic characteristics[J]. Acta Physica Sinica, 2013,62(2): 020506.
[15]	张春涛, 马千里, 彭宏 . 基于信息熵优化相空间重构参数的混沌时间序列预测[J]. 物理学报, 2010,59(11): 7623-7629.
	ZHANG C T , MA Q L , PENG H . Chaotic time series prediction based on information entropy optimized parameters of phase space reconstruction[J]. Acta Physica Sinica, 2010,59(11): 7623-7629.
[16]	侯站 . 基于预测的相空间重构技术研究[D]. 郑州:郑州大学, 2010.
	HOU Z . Research on phase space reconstruction based on prediction[D]. Zhengzhou:Zhengzhou University, 2010.
[17]	GRASSBERGER P , PROCACCIA I . Measuring the strangeness of strange attractors[J]. Physica D, 1983,9(1,2): 189-208.
[18]	JOVIC B , UNSWORTH C P . Fast synchronization of chaotic maps for secure chaotic communications[J]. Electronics Letters, 2010,46(1): 49-50.
[19]	DENNEDY J , EBERHART R C . Particle swarm optimization[C]// The IEEE International Conference on Neural Networks. 1995: 1942-1948.

监测点	2012年/条	2013年/条	2014年/条	2015年/条	总计/条
amw	53万	38万	57万	64万	212万
san	67万	36万	63万	69万	235万
bcn	67万	42万	51万	69万	229万
mnl	68万	25万	48万	65万	206万

监测点	区间1	区间2
amw	10,50]	60,120]
san	30,60]	90,130]
bcn	15,55]	55,115]
mnl	110,140]	160,220]

监测点的访问时间区间	访问时间的均值/ms	访问时间的标准差	访问时间的中位数/ms	访问直径的均值/跳	访问直径的标准差	访问直径的中位数	Pearson相关系数
amw[10,50]	30.592 2	9.314 9	29.941 2	14.498	3.569 8	14	0.176
amw[60,120]	88.530 2	15.489 9	88.011 2	15.773	3.854	16	0.132
san[30,60]	44.829 7	8.544 2	45.300 7	15.492	3.607 7	15	0.201
san[90,130]	102.622 8	10.071 9	102.329 1	16.788	3.525 6	17	0.068
mnl[110,140]	127.397 3	9.680 3	126.675	16.394	3.444 7	16	0.091
mnl[160,220]	182.339 2	14.914 1	181.505	15.483	3.442 6	15	0.098
bcn[15,55]	35.677	8.062 1	35.311 4	15.228	2.705 2	15	0.164
bcn[55,115]	81.792	15.138 2	78.991 4	17.448	3.343 7	17	0.092

监测点	拟合准确度	预测准确度
amw	95.02%	92.89%
bcn	96.84%	92.65%
san	96.31%	93.58%
mnl	96.78%	94.09%

互联网传播行为的时序演化与预测

Timing evolution and prediction of Internet transmission behavior

在线阅读

PDF下载

可视化

摘要/Abstract

引用本文

使用本文

图/表 13

参考文献 19

相关文章 4

Metrics

推荐阅读 0

[1]	李致远,陈汝龙,王汝传. 基于兴趣和行为预测的移动社交网络动态资源发现机制[J]. 通信学报, 2016, 37(4): 34-43.
[2]	赵泽,尚鹏飞,陈海明,刘强,李栋,张招亮,崔莉. 无线传感器网络干扰分类识别机制的研究[J]. 通信学报, 2013, 34(10): 28-36.
[3]	赵泽1,2，尚鹏飞1,2，陈海明1，刘强1，李栋1，张招亮1,2，崔莉1. 无线传感器网络干扰分类识别机制的研究[J]. 通信学报, 2013, 34(10): 4-36.
[4]	徐野,赵海,苏威积,张文波,张昕,王祖伟. Internet的IP基密度分析[J]. 通信学报, 2005, 26(11): 125-131.