基于改进粒子群算法优化回声状态网络的时间序列预测
Time Series Forecasting Based on Echo State Network Optimized by Improved Particle Swarm Algorithm

DOI: 10.12677/CSA.2021.118212, PP. 2070-2079

Keywords: 时间序列预测，回声状态网络，粒子群优化算法
Time Series Prediction, ESN, Particle Swarm Optimization Algorithm

Full-Text   Cite this paper   Add to My Lib

Abstract:

由于结构简单、收敛速度快等优点，回声状态网络(Echo State Network, ESN)已被广泛的用于时间序列的预测。针对回声状态网络中随机生成权值矩阵带来的不适用于特定时间序列的问题，本文提出利用改进的粒子群优化算法来优化回声状态网络部分随机权值。与标准粒子群优化算法相比，惯性权重和学习因子自适应调整，以提高算法的寻优性能。为验证本文方法的有效性，对Mackey-Glass时间序列、非线性自回归滑动模型(Nonlinear Auto Regressive Moving Average, NARMA)和Lorenz时间序列进行仿真实验。实验结果表明，本文提出的方法可以进一步提升回声状态网络对时间序列的预测精度。
Echo State Network (ESN) has been widely used in time series prediction due to its simple structure and fast convergence speed. In order to solve the problem that random weight matrix generated in ESN is not applicable to specific time series, an improved particle swarm optimization (PSO) algorithm is proposed to optimize partial random weights in ESN. Compared with the standard particle swarm optimization algorithm, the inertia weight and learning factor are adjusted to improve the optimization performance of the algorithm. To verify the effectiveness of the proposed method, the Mackey-Glass time series, the nonlinear autoregressive sliding model (NARMA) and the Lorenz time series are simulated. Experimental results show that the method proposed in this paper can further improve the prediction accuracy of ESN for time series.

References

[1]	Bar-Joseph, Z., Gerber, G.K., Gifford, D.K., Jaakkola, T.S. and Simon, I. (2003) Continuous Representations of Time-Series Gene Expression n Data. Journal of Computational Biology: A Journal of Computational Molecular Cell Bi-ology, 10, 341-356. https://doi.org/10.1089/10665270360688057
[2]	李兴兴. 金融时间序列的建模与预测[D]: [硕士学位论文]. 杭州: 杭州电子科技大学, 2018.
[3]	张帆. 基于神经网络的交通流时间序列预测[J]. 现代信息科技, 2020, 4(23): 87-89, 93.
[4]	Billinton, R., Hua, C. and Ghajar, R. (1996) Time-Series Models for Reliability Evaluation of Power Systems Including Wind Energy. Microelectronics Reliability, 36, 1253-1261. https://doi.org/10.1016/0026-2714(95)00154-9
[5]	Ghil, M. and Vautard, R. (1991) Interdecadal Oscillations and the Warming Trend in Global Temperature Time Series. Nature, 350, 324-327. https://doi.org/10.1038/350324a0
[6]	Chisci, L., Mavino, A., Perferi, G., Sciandrone, M., Anile, C., Colicchio, G., et al. (2010) Real-Time Epileptic Seizure Prediction Using AR Models and Support Vector Machines. IEEE Transac-tions on Biomedical Engineering, 57, 1124-1132. https://doi.org/10.1109/TBME.2009.2038990
[7]	Laner, M., Svoboda, P. and Rupp, M. (2013) Parsimonious Fitting of Long-Range Dependent Network Traffic Using ARMA Models. IEEE Communications Letters, 17, 2368-2371. https://doi.org/10.1109/LCOMM.2013.102613.131853
[8]	Narendra, B.C. and Eswara, R.B. (2014) A Moving-Average Filter Based Hybrid ARIMA-ANN Model for Forecasting Time Series Data. Applied Soft Compu-ting, 23, 27-38. https://doi.org/10.1016/j.asoc.2014.05.028
[9]	孟庆芳, 陈珊珊, 陈月辉, 冯志全. 基于递归量化分析与支持向量机的癫痫脑电自动检测方法[J]. 物理学报, 2014(5): 1-8.
[10]	Li, K., Han, Y. and Huang, H.Q. (2016) Chaotic Time Series Prediction Based on IBH-LSSVM and Its Application to Short-Term Prediction of Dynamic Fluid Level of the Oil Wells. Information and Control, 45, 241-247.
[11]	梁智珲. 遗传算法优化前向神经网络结构和权重矢量研究[J]. 信息与电脑(理论版), 2019(14): 37-38, 43.
[12]	Jaeger, H. and Haas, H. (2004) Harnessing Nonlinearity: Predicting Chaotic Systems and Saving Energy in Wireless Communication. Science, 304, 78-80. https://doi.org/10.1126/science.1091277
[13]	韩莹, 井元伟, 金建宇, 李琨. 基于改进黑洞算法优化ESN的网络流量短期预测[J]. 东北大学学报(自然科学版), 2018, 39(3): 311-315.
[14]	Wang, H.S. and Yan, X.F. (2015) Op-timizing the Echo State Network with a Binary Particle Swarm Optimization Algorithm. Knowledge Based Systems, 86, 182-193. https://doi.org/10.1016/j.knosys.2015.06.003
[15]	Chouikhi, N., Ammar, B., Rokbani, N. and Alimi, A.M. (2017) PSO-Based Analysis of Echo State Network Parameters for Time Series for Ecasting. Applied Soft Compu-ting, 55, 211-225. https://doi.org/10.1016/j.asoc.2017.01.049
[16]	彭宇, 王建民, 彭喜元. 基于回声状态网络的时间序列预测方法研究[J]. 电子学报, 2010, 38(z1): 148-154.
[17]	Chen, H.C. and Wei, D.Q. (2021) Chaotic Time Series Prediction Using Echo State Network Based on Selective Opposition Grey Wolf Optimizer. Nonlinear Dynamics, 104, 3925-3935. https://doi.org/10.1007/s11071-021-06452-w
[18]	任条娟, 钟陈健, 刘半藤, 郑启航. 基于弹性小世界回声状态网络的非线性时间序列预测[J]. 计算机应用与软件, 2021, 38(6): 256-261.
[19]	Li, D.Y., Liu, F., Qiao, J.F. and Li, R. (2019) Structure Optimization for Echo State Network Based on Contribution. Tsinghua Science and Technology, 24, 97-105. https://doi.org/10.26599/TST.2018.9010049
[20]	史柏迪, 庄曙东, 韩祺. 基于改进的粒子群优化神经网络粗糙度预测模型[J]. 组合机床与自动化加工技术, 2021(2): 30-33+38.
[21]	张春韵, 邹德旋, 沈鑫. 改进的粒子群算法在电力经济调度中的应用[J]. 制造业自动化, 2021, 43(1): 53-57+64.
[22]	韩顺杰, 单新超,于爱君, 符金鑫. 基于改进粒子群算法的工业机器人轨迹规划[J]. 制造技术与机床, 2021(4): 8-14.

Full-Text