﻿ 混沌时间序列的局域多项式系数建模及预测

# 混沌时间序列的局域多项式系数建模及预测Local Polynomial Coefficient AR Prediction Model for Chaotic Time Series

Abstract: The local linear model, being widely studied and used to predict chaotic time series, has a history of over thirty years. Because of its simple structure, it is easy to implement. However, the local linear method cannot effectively fit nonlinear characteristics of chaotic time series. According to the local and nonlinear characteristics of chaotic time series, a local polynomial coefficient autoregressive prediction model is proposed, namely, local nonlinear prediction model, based on local linear model. Compared to the local linear model, local nonlinear prediction model can approximate many effec-tively nonlinear properties of chaotic time series. The simulation results of three typical chaotic time series (Logistic mapping, Henon mapping and Lorenz system) show that prediction performance and stability of local nonlinear multi-step model are better than the local linear model. Moreover, the presented model has higher prediction accuracy, even under the circumstances of less sample data.

[1] 张家树, 肖先赐 (2000) 混沌时间序列的自适应高阶非线性滤波预测. 物理学报, 7, 1221-1227.

[2] 张森, 肖先赐 (2005) 混沌时间序列全局预测新方法——连分式法. 物理学报, 11, 5062-5068.

[3] Li, H.C., Zhang, J.S. and Xiao, X.C. (2005) Neural Volterra filter for chaotic time series prediction. Chinese Physics, 14, 2181.

[4] Su, L.Y. (2010) Prediction of multivariate chaotic time series with local polynomial fitting. Computers & Mathematics with Ap-plications, 59, 737-744.

[5] Su, L.Y., Ma, Y.J. and Li, J.J. (2012) Application of local polynomial estimation in sup-pressing strong chaotic noise. Chinese Physics B, 21, Article ID: 020508.

[6] 周永道, 马洪, 吕王勇, 王会琦 (2007) 基于多元局部多项式方法的混沌时间序列预测. 物理学报, 56, 6809- 6814.

[7] 韩敏 (2007) 混沌时间序列预测理论与方法(第1卷). 中国水利水电出版社, 北京, 1.

[8] She, D.X. and Yang, X.H. (2010) A new adaptive local linear prediction method and its application in hydrological time series. Mathematical Problems in Engineering, 2010, Article ID: 205438.

[9] 张学清, 梁军 (2013) 基于 EEMD-近似熵和储备池的风电功率混沌时间序列预测模型.物理学报, 62, 1-10.

[10] 张玉梅, 吴晓军, 白树林 (2013) 交通流量序列混沌特性分析及DFPSOVF预测模型.物理学报, 62, Article ID: 190509.

[11] 张玉梅, 曲仕茹, 秦小娜 (2013) 基于DFP的自适应算法及其在短时交通流预测中的应用. 西北工业大学学报, 3, 482-486.

[12] 张玉梅, 白树林 (2012) 基于乘积耦合Volterra模型的短时交通流预测. 计算机应用, 3, 843-846.

[13] 张玉梅, 吴晓军, 白树林 (2013) 基于DFP的二阶Volterra滤波器及其在混沌序列预测中的应用. 中国科学: 物理学 力学 天文学, 4, 530-537.

[14] Jaeger, H. and Haas, H. (2004) Harnessing nonlinearity: Predicting chaotic systems and saving energy in wireless telecommunication. Science, 308, 78-80.

[15] 史志伟, 韩敏 (2007) ESN 岭回归学习算法及混沌时间序列预测. 控制与决策, 3, 258-262.

[16] 韩敏, 史志伟, 郭伟 (2007) 储备池状态空间重构与混沌时间序列预测. 物理学报, 1, 43-50.

[17] 宋彤, 李菡 (2012) 基于小波回声状态网络的混沌时间序列预测. 物理学报, 8, Article ID: 080506.

[18] 王新迎, 韩敏 (2012) 基于极端学习机的多变量混沌时间序列预测. 物理学报, 8, Article ID: 080507.

[19] 韩敏, 王新迎 (2013) 多元混沌时间序列的加权极端学习机预测. 控制理论与应用, 11, 1467-1472.

[20] Suykens, J.A.K. and Vandewalle, J. (1999) Least squares support vector machine classifiers. Neural Processing Letters, 9, 293-300.

[21] 韩敏, 许美玲 (2013) 一种基于误差补偿的多元混沌时间序列混合预测模型. 物理学报, 12, Article ID: 120510.

[22] 叶美盈, 汪晓东, 张浩然 (2005) 基于最小二乘支持向量机建模的混沌系统控制. 物理学报, 6, 2568-2573.

[23] 肖支才, 王杰, 王永生 (2010) 基于在线 LSSVM算法的变参数混沌时间序列预测. 航空计算技术, 3, 29-33.

[24] 温祥西, 孟相如, 李明迅 (2013) 基于最优样本子集的在线模糊LSSVM混沌时间序列预测. 应用科学学报, 4, 411.

[25] 赵永平, 张丽艳, 李德才, 王立峰, 蒋洪章 (2013) 过滤窗最小二乘支持向量机的混沌时间序列预测. 物理学报, 12, Article ID: 120511.

[26] 唐舟进, 任峰, 彭涛, 王文博 (2013) 基于迭代误差补偿的混沌时间序列最小二乘支持向量机预测算法. 物理学报, 5, Article ID: 050505.

[27] 席剑辉, 韩敏 (2007) 主成分分析与神经网络的结合在多变量序列预测中的应用. 控制理论与应用, 5, 719-724.

[28] Meng, Q. and Peng, Y. (2007) A new local linear prediction model for chaotic time series. Physics Letters A, 370, 465-470.

[29] 吕永乐 (2012) 一种新的统计预测模型——多项式系数自回归模型. 计算机工程与应用, 3, 237-241.

[30] Takens, F. (1981) Detecting strange attractors in turbulence. In: Rand, D.A. and Young, L.-S., Eds., Dynamical Systems and Turbulence, Lecture Notes in Mathematics, Volume 898, Springer-Verlag, Berlin, 366-381.

[31] Cao, L.Y. (1997) Practical method for determining the minimum embedding dimension of a scalar time series. Physica D: Nonlinear Phenomena, 110, 43-50.

Top