基于KPCA优化ESN的网络流量预测方法
Network traffic prediction method based on KPCA optimized ESN
查看参考文献23篇
|
文摘
|
为了提高网络流量的预测精确度,提出一种核主成分分析(KPCA)优化回声状态网络(ESN)的网络流量预测方法。首先利用相空间重构对网络流量序列进行处理,提高序列的可预测性,然后对网络流量序列进行核主成分分析,提取序列中的有效信息,通过实验方法确定回声状态网络的储备池参数,最后利用回声状态网络对网络流量进行预测。与标准回声状态网络、差分自回归滑动平均模型(ARIMA)、以及最小二乘支持向量机(LSSVM)预测模型进行了仿真对比,结果表明提出的方法具有更高的预测精确度以及更小的预测误差,同时一定程度上减少了预测时间。 |
|
其他语种文摘
|
In order to improve the prediction accuracy of network traffic, a network traffic prediction method based on kernel principal component analysis (KPCA) optimized echo state network (ESN) was proposed. Firstly, network traffic series was processed to improve the predictability by phase space reconstruction,then the effective information was extracted through kernel principal component analysis. The reservoir parameters of echo state network were determined through the experiment method. Finally, network traffic was predicted through the echo state network. The proposed method is compared with standard echo state netowrk,auto regressive integrated moving average (ARIMA),and least squares support vector machine (LSSVM) predictive model. The simulation results show that the proposed method has higher prediction accuracy with smaller predictive error, at the same time the prediction time is reduced. |
|
来源
|
电机与控制学报
,2015,19(12):114-120 【核心库】
|
|
DOI
|
10.15938/j.emc.2015.12.017
|
|
关键词
|
网络流量
;
预测
;
回声状态网络
;
核主成分分析
;
相空间重构
|
|
地址
|
1.
沈阳工业大学信息科学与工程学院, 辽宁, 沈阳, 110870
2.
东北大学信息科学与工程学院, 辽宁, 沈阳, 110819
|
|
语种
|
中文 |
|
文献类型
|
研究性论文 |
|
ISSN
|
1007-449X |
|
学科
|
自动化技术、计算机技术 |
|
基金
|
国家自然科学基金
;
辽宁省博士启动基金
|
|
文献收藏号
|
CSCD:5594163
|
参考文献 共
23
共2页
|
|
1.
Qu H. Prediction Method for Network Traffic Based on Maximum Correntropy Criterion.
China Communications,2013(1):134-145
|
被引
8
次
|
|
|
|
|
2.
孙广路. 基于混合方法的流量测量系统.
电机与控制学报,2011,15(6):91-96
|
被引
2
次
|
|
|
|
|
3.
高波. 基于EMD及ARMA的自相似网络流量预测.
通信学报,2011,32(4):47-56
|
被引
45
次
|
|
|
|
|
4.
Laner M. Parsimonious fitting of long-range dependent network traffic using ARMA models.
IEEE Communications Letters,2013,17(12):2368-2371
|
被引
11
次
|
|
|
|
|
5.
Wang J. A process level network traffic prediction algorithm based on ARIMA model in smart substation.
2013 IEEE International Conference on Signal Processing, Communications and Computing,2013:1-5
|
被引
1
次
|
|
|
|
|
6.
Yadav R K. Comparative evaluation of ARIMA and ANFIS for modeling of wireless network traffic time series.
Eurasip Journal on Wireless Communications and Networking,2014(1):15
|
被引
6
次
|
|
|
|
|
7.
Ren X Y. Parameter estimation and application of time-varying FARIMA model.
International Journal of Advancements in Computing Technology,2011,3(3):89-94
|
被引
5
次
|
|
|
|
|
8.
姜明. 网络流量预测中的时间序列模型比较研究.
电子学报,2009,37(11):2353-2358
|
被引
52
次
|
|
|
|
|
9.
Uux W. A short-term forecasting algorithm for network traffic based on chaos theory and SVM.
Journal of Network and Systems Management,2011,19(4):427-447
|
被引
1
次
|
|
|
|
|
10.
孟庆芳. 基于局域相关向量机回归模型的小尺度网络流量的非线性预测.
物理学报,2013,62(15):150509
|
被引
4
次
|
|
|
|
|
11.
唐舟进. 一种基于相关分析的局域最小二乘支持向量机小尺度网络流量预测算法.
物理学报,2014,63(13):130504
|
被引
5
次
|
|
|
|
|
12.
田中大. 用于混沌时间序列预测的组合核函数最小二乘支持向量机.
物理学报,2014,63(16):160508
|
被引
14
次
|
|
|
|
|
13.
Wang J S. Prediction of internet traffic based on Elman neural network.
Chinese Control and Decision Conference,2009:1248-1252
|
被引
4
次
|
|
|
|
|
14.
Li X B. RBF neural network optimized by particle swarm optimization for forecasting urban traffic flow.
3rd International Symposium on Intelligent Information Technology Application,2009:124-127
|
被引
2
次
|
|
|
|
|
15.
孙韩林. 粗粒度网络流量的灰色模型预测.
北京邮电大学学报,2010,33(1):7-11
|
被引
12
次
|
|
|
|
|
16.
Frank Z. Traffic network state estimation using extended Kalman filtering and DSMART.
IFAC Proceedings Volumes,2006,11(1):37-42
|
被引
1
次
|
|
|
|
|
17.
Jaeger H.
The "echo state" Approach to Analyzing and Training Recurrent Neural Network. GMD Report 148,2001
|
被引
2
次
|
|
|
|
|
18.
Qian G. Multiresolution-based echo state network and its application to the longterm prediction of network traffic.
Proceedings of the 2008 International Symposium on Computational Intelligence and Design,2008:469-472
|
被引
1
次
|
|
|
|
|
19.
冯辰.
基于ESN的网络流量预测算法研究,2013
|
被引
1
次
|
|
|
|
|
20.
Kim H S. Nonlinear dynamics delay times, and embedding windows.
Physica D,1999,127(1):48-60
|
被引
292
次
|
|
|
|
|
了解气象卫星更多信息，请访问