基于MEEMD-PE与CS-WNN模型的网络时延预测

doi:10.3969/j.issn.1001-506X.2020.01.25

摘要/Abstract

摘要：

针对网络控制系统诱导时延具有的随机性、非平稳性、非线性等特点，提出了一种基于改进的集总平均经验模态分解（modified ensemble empirical mode decomposition，MEEMD）-排列熵和布谷鸟搜索（cuckoo search，CS）优化的小波神经网络（wavelet neural network，WNN）时延预测算法。首先通过MEEMD对网络诱导时延序列进行处理，分别计算各模态的排列熵值，对复杂度相近的模态进行重组后得到新的子序列，从而达到降低建模复杂度和减少计算量的目的；然后利用CS算法优化的WNN预测新的子序列；最后叠加各子序列预测结果以获得时延序列的最终预测值。仿真表明，该算法具有较好的预测精度，能反映时延序列的总体趋势，可有效地降低异常值影响等优点。

关键词: 网络控制系统, 改进的集总平均经验模态分解, 排列熵, 布谷鸟算法, 小波神经网络, 时延预测

Abstract:

Aiming at the characteristics of randomness, instability and nonlinear induced delay of networked control system, a delay prediction algorithm of modified ensemble empirical mode decomposition-permutation entropy (MEEMD-PE) and wavelet neural network (WNN) optimized by cuckoo search (CS) is proposed. Firstly, MEEMD is used to decompose the original delay sequence, then the permutation entropy values of each sub sequence are calculated and recombination of new subsequences to reduce the non-stationary characteristics of the delay sequence and amount of calculation. And then predict the new subsequences by the WNN optimized by the CS algorithm. The final results of network delay are calculated by superimposing the prediction of the submodels. Simulation results show that the method has the advantages of better prediction accuracy, reflecting the overall trend of the delay sequence, and effectively reducing the impact of outliers.

Key words: networked control system, modified ensemble empirical mode decomposition (MEEMD), permutation entropy, cuckoo search (CS), wavelet neural network (WNN), delay prediction

中图分类号:

TP273

时维国, 国明. 基于MEEMD-PE与CS-WNN模型的网络时延预测[J]. 系统工程与电子技术, 2020, 42(1): 184-190.

Weiguo SHI, Ming GUO. Network delay prediction based on model of modified ensemble empirical mode decomposition-permutation entropy and cuckoo search-wavelet neural network[J]. Systems Engineering and Electronics, 2020, 42(1): 184-190.

图/表 10

图1

图2

图3

图4

表1

图5

表2

图6

图7

表3

参考文献 26

1	OGURA M , CETINKAYA A , HAYAKAWA T , et al. State-feedback control of Markov jump linear systems with hidden-Markov mode observation[J]. Automatica, 2018, 89, 65- 72. doi: 10.1016/j.automatica.2017.11.022
2	CAI H B , LI P , SU C L , et al. Robust model predictive control for a class of discrete-time markovian jump linear systems with operation mode disordering[J]. IEEE Access, 2019, 7, 10415- 10427. doi: 10.1109/ACCESS.2019.2891506
3	时维国, 邵诚, 孙正阳. 基于AR模型时延预测的改进GPC网络控制算法[J]. 控制与决策, 2012, 27 (3): 477- 480.
	SHI W G , SHAO C , SUN Z Y . Improved GPC network-control algorithm based on AR model time-delay prediction[J]. Control and Decision, 2012, 27 (3): 477- 480.
4	刘婷, 姜顺, 潘丰. 网络控制系统前向通道随机时延的在线多步预测[J]. 信息与控制, 2017, 46 (5): 620- 626.
	LIU T , JIANG S , PAN F . Online multi-step prediction for the random delay of the forward channel in networked control system[J]. Information and Control, 2017, 46 (5): 620- 626.
5	李君, 刘斌, 蒋峥. 基于时延灰色预测的网络机器人网络预测控制[J]. 计算机仿真, 2016, 33 (1): 331- 335. doi: 10.3969/j.issn.1006-9348.2016.01.071
	LI J , LIU B , JIANG Z . Networked predictive control of internet-based telerobotics based on grey prediction of delay[J]. Computer Simulation, 2016, 33 (1): 331- 335. doi: 10.3969/j.issn.1006-9348.2016.01.071
6	李世峰, 邱占芝, 樊丽萍, 等. 基于改进BP网络的网络控制系统建模与仿真[J]. 系统仿真学报, 2018, 30 (6): 2279- 2287.
	LI S F , QIU Z Z , FAN L P , et al. Modeling and simulation of networked control systems based on improved BP network[J]. Journal of System Simulation, 2018, 30 (6): 2279- 2287.
7	邱占芝, 李世峰. 基于神经网络的PID网络化控制系统建模与仿真[J]. 系统仿真学报, 2018, 30 (4): 1423- 1432.
	QIU Z Z , LI S F . Modeling and simulation of pid networked control system based on neural networked[J]. Journal of System Simulation, 2018, 30 (4): 1423- 1432.
8	YANG B , LI H . A novel convolutional neural network based approach to predictions of process dynamic time delay sequences[J]. Chemometrics and Intelligent Laboratory Systems, 2018, 174, 56- 61. doi: 10.1016/j.chemolab.2018.01.012
9	田中大, 高宪文, 李琨. 基于KPCA与LSSVM的网络控制系统时延预测方法[J]. 系统工程与电子技术, 2013, 35 (6): 1281- 1285.
	TIAN Z D , GAO X W , LI K . Networked control system time-delay prediction method based on KPCA and LSSVM[J]. Systems Engineering and Electronics, 2013, 35 (6): 1281- 1285.
10	RIBEIRO G T , MARIANI V C , COELHO L D S . Enhanced ensemble structures using wavelet neural networks applied to short-term load forecasting[J]. Engineering Applications of Artificial Intelligence, 2019, 82, 272- 281. doi: 10.1016/j.engappai.2019.03.012
11	刘经纬, 周瑞, 赵辉, 等. 预测小波神经网络智能控制系统仿真研究[J]. 系统仿真学报, 2018, 30 (10): 3770- 3780.
	LIU J W , ZHOU R , ZHAO H , et al. Simulation research on predictive wavelet neural network intelligent control system[J]. Journal of System Simulation, 2018, 30 (10): 3770- 3780.
12	田中大, 张超, 李树江, 等. 基于相空间重构与最小二乘支持向量机的时延预测[J]. 电子学报, 2017, 45 (5): 1044- 1051. doi: 10.3969/j.issn.0372-2112.2017.05.003
	TIAN Z D , ZHANG C , LI S J , et al. Time-delay prediction based on phase space reconstruction and least squares support vector machine[J]. Chinese Journal of Electronics, 2017, 45 (5): 1044- 1051. doi: 10.3969/j.issn.0372-2112.2017.05.003
13	时维国, 许超. 基于相空间重构与鲁棒极限学习机的时延预测[J]. 系统工程与电子技术, 2019, 41 (2): 417- 422.
	SHI W G , XU C . Delay prediction based on phase space reconstruction and robust extreme learning machine[J]. Systems Engineering and Electronics, 2019, 41 (2): 417- 422.
14	田中大, 高宪文, 李琨. 基于EMD与LS-SVM的网络控制系统时延预测方法[J]. 电子学报, 2014, 42 (5): 868- 874. doi: 10.3969/j.issn.0372-2112.2014.05.006
	TIAN Z D , GAO X W , LI K . Time-delay prediction method of networked control system based on EMD and LS-SVM[J]. Acta Electronica Sinica, 2014, 42 (5): 868- 874. doi: 10.3969/j.issn.0372-2112.2014.05.006
15	HUANG N E , ZHENG S , LONG S R , et al. The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis[J]. Proceedings Mathematical Physical & Engineering Sciences, 1998, 454 (1971): 903- 995.
16	WU Z , HUANG N E . Ensemble empirical mode decomposition:a noise-assisted data analysis method[J]. Advances in Adaptive Data Analysis, 2009, 1 (1): 1- 41.
17	郑旭, 郝志勇, 金阳, 等. 基于MEEMD的内燃机辐射噪声贡献[J]. 浙江大学学报(工学版), 2012, 46 (5): 954- 960. doi: 10.3785/j.issn.1008-973X.2012.05.029
	ZHENG X , HAO Z Y , JIN Y , et al. Studying noise contributions of IC engine via MEEMD method[J]. Journal of Zhejiang University (Engineering Science), 2012, 46 (5): 954- 960. doi: 10.3785/j.issn.1008-973X.2012.05.029
18	XIE S F , LIANG Y J , ZHENG Z T , et al. Combined forecasting method of landslide deformation based on MEEMD, approximate entropy, and WLS-SVM[J]. ISPRS International Journal of Geo-Information, 2017, 6 (1) doi: 10.3390/ijgi6010005
19	ABBAD A , ELHARROUSS O , ABBAD K , et al. Application of MEEMD in post-processing of dimensionality reduction methods for face recognition[J]. IET Biometrics, 2019, 8 (1): 59- 68.
20	DAI S , CHEN Q , DAI H . De-noising algorithm for flight data recording system based on modified ensemble empirical mode decomposition[J]. Journal of Physics:Conference Series, 2019, 1267. doi: 10.1088/1742-6596/1267/1/012024
21	BANDT C , POMPE B . Permutation entropy:a natural complexity measure for time series[J]. Physical Review Letters, 2002, 88 (17) doi: 10.1103/PhysRevLett.88.174102
22	CHEN Y , LUH P B , GUAN C , et al. Short-term load forecasting:similar day-based wavelet neural networks[J]. IEEE Trans.on Power Systems, 2010, 25 (1): 322- 330.
23	CHE G , LUH P B , COOLBETH M A , et al. Very short-term load forecasting:multilevel wavelet neural networks with data pre-filtering[J]. IEEE Trans.on Power Systems, 2013, 28 (1): 30- 41.
24	YANG X S, DEB S. Cuckoo search via Levy flights[C]//Proc.of the World Congress on Nature & Biologically Inspired Computing, 2009: 210-214.
25	YANG X S , DEB S . Engineering optimisation by Cuckoo search[J]. International Journal of Mathematical Modelling & Numerical Optimisation, 2010, 11 (4): 330- 343.
26	LI S T, CHEN S C. Function approximation using robust wavelet neural networks[C]//Proc.of the IEEE International Conference on Tools with Artificial Intelligence, 2002: 483-488.

算法	完备性指标	整体正交性指标	分量数
EMD	4.996 3	0.217 3	7
MEEMD	2.397 9	0.063 2	9

新序列号	1	2	3	4	5
原模态序列号	1	2	3, 4	5, 6	7, 8, 9

预测方法	RMSE	MAPE	训练时间/s
本文方法	0.218	0.150	3.718
EMD-CS-WNN	1.507	1.366	5.045
EMD-LSSVM	2.382	1.903	10.981
CS-WNN	2.245	2.103	3.596
PSO-WNN	3.297	2.404	22.912
CS-BP	5.878	2.698	10.243

[1]	时维国, 国明. 鲸鱼优化相关向量机的网络控制系统变采样周期调度[J]. 系统工程与电子技术, 2020, 42(10): 2348-2355.
[2]	金杉, 金志刚. 基于模糊小波聚类混合的多目标覆盖质量评估方法[J]. 系统工程与电子技术, 2019, 41(6): 1316-1323.
[3]	时维国, 许超. 基于相空间重构与鲁棒极限学习机的时延预测[J]. 系统工程与电子技术, 2019, 41(2): 416-421.
[4]	刘明骞, 颜志文, 张俊林. 空中目标辐射源的个体识别方法[J]. 系统工程与电子技术, 2019, 41(11): 2408-2415.
[5]	赵顺利1, 尹逊和1, 魏学业1, LAM Hakkeung2. 基于模型的网络控制系统设计:切换控制的平均驻留时间法[J]. 系统工程与电子技术, 2016, 38(8): 1899-1908.
[6]	马巧利, 周川, 陈兰浪. 网络控制系统的事件触发与量化控制协同设计[J]. 系统工程与电子技术, 2016, 38(3): 652-657.
[7]	尹艳玲1, 王泰华1, 曾旗2. 基于2D模型的网络系统迭代学习控制设计方法[J]. 系统工程与电子技术, 2015, 37(5): 1157-1162.
[8]	秦强，冯蕴雯，薛小锋. 改进布谷鸟算法在结构可靠性分析中的应用[J]. 系统工程与电子技术, 2015, 37(4): 979-984.
[9]	马奥家，董朝阳，王青，牛尔卓. 基于异步切换的飞行器网络控制系统故障检测[J]. 系统工程与电子技术, 2014, 36(5): 940-946.
[10]	尹逊和, 樊雪丽, 张红. 基于异步动态的多机器人系统的一致性[J]. 系统工程与电子技术, 2014, 36(12): 2426-2434.
[11]	田中大，高宪文，李琨. 基于KPCA与LSSVM的网络控制系统时延预测方法[J]. Journal of Systems Engineering and Electronics, 2013, 35(6): 1281-1285.
[12]	田中大, 高宪文，李琨. 基于预测控制的NCS时延补偿算法[J]. 系统工程与电子技术, 2013, 35(10): 2165-2169.
[13]	黄丽莲, 陈瑾. 基于Smith补偿与神经网络的网络控制系统PD控制[J]. Journal of Systems Engineering and Electronics, 2012, 34(9): 1884-1888.
[14]	陈刚，阳春华，朱红求. 考虑时延与丢包的网络控制系统分析与综合[J]. Journal of Systems Engineering and Electronics, 2012, 34(2): 342-347.
[15]	谢德晓, 黄鹤, 张登峰, 王执铨. 随机时延网络控制系统的鲁棒H_∞状态反馈控制[J]. Journal of Systems Engineering and Electronics, 2011, 33(9): 2072-2078.