Abstract
In this brief, considering the infinite memory of fractional-order differential equation, a fractional-order echo state network (FESN) is given for time series prediction. For the FESN, the reservoir state differential equation is replaced with fractional-order differential equation. According to the advantages of FESN, the dynamic characteristics of a class of time series can be fully reflected. In order to improve the prediction performance of FESN, a fractional-order output weights learning method and a fractional-order parameter optimization method are given to train the output weights and optimize the reservoir parameters, respectively. Finally, two numerical examples are used to show the effectiveness of FESN.
Similar content being viewed by others
References
Jaeger H, Haas H (2004) Harnessing nonlinearity: predicting chaotic systems and saving energy in wireless telecommunication. Science 304(5667):78–80
Jaeger H (2010) The ‘echo state’ approach to analysing and training recurrent neural networks–with an Erratum note. German National Research Center for Information Technology, GMD Report 148,
Zhang HG, Wang ZS, Liu DR (2014) A comprehensive review of stability analysis of continuous-time recurrent neural networks. IEEE Trans Neural Netw Learn Syst 25(7):1229–1262
Jaeger H, Lukoševičius M, Popovici D, Siewert U (2007) Optimization and applications of echo state networks with leaky-integrator neurons. Neural Netw 20(3):335–352
Han M, Xu ML (2018) Laplacian echo state network for multivariate time series prediction. IEEE Trans Neural Netw Learn Syst 29(1):238–244
Shi G, Liu DR, Wei QL (2016) Energy consumption prediction of office buildings based on echo state networks. Neurocomputing 216:478–488
Xue FZ, Li Q, Li XM (2017) The combination of circle topology and leaky integrator neurons remarkably improves the performance of echo state network on time series prediction. PloS One 12(7):e0181816
Sun XC, Li T, Li Q, Huang Y, Li YQ (2017) Deep belief echo-state network and its application to time series prediction. Knowl-Based Syst 130:17–29
Wang HS, Yan XF (2015) Optimizing the echo state network with a binary particle swarm optimization algorithm. Knowl-Based Syst 86:182–193
Magerl M, Ceperic V, Baric A (2016) Echo state networks for black-box modeling of integrated circuits. IEEE Trans Comput-Aided Des Integr Circuits Syst 35(8):1309–1317
Yao XS, Wang ZS, Zhang HG (2018) Identification method for a class of periodic discrete-time dynamic nonlinear systems based on sinusoidal ESN. Neurocomputing 275:1511–1521
Han SI, Lee JM (2014) Fuzzy echo state neural networks and funnel dynamic surface control for prescribed performance of a nonlinear dynamic system. IEEE Trans Ind Electron 61(2):1099–1112
Kaslik E, Sivasundaram S (2012) Nonlinear dynamics and chaos in fractional-order neural networks. Neural Netw 32:245–256
Podlubny I (1998) Fractional differential equations. Elsevier, Amsterdam
Guo BL, Pu XK, Huang FH (2015) Fractional partial differential equations and their numerical solutions. World Scientific, Singapore
Yang Y, Xue DY (2017) Modified grey model predictor design using optimal fractional-order accumulation calculus. IEEE/CAA J Autom Sinica 4(4):724–733
Xiao M, Jiang GP, Cao JD, Zheng WX (2017) Local bifurcation analysis of a delayed fractional-order dynamic model of dual congestion control algorithms. IEEE/CAA J Autom Sinica 4(2):361–369
Qiao JF, Li FJ, Han HG, Li WJ (2017) Growing echo-state network with multiple subreservoirs. IEEE Trans Neural Netw Learn Syst 28(2):391–404
Scardapane S, Panella M, Comminiello D, Hussain A, Uncini A (2016) Distributed reservoir computing with sparse readouts. IEEE Comput Intell Mag 11(4):59–70
Soto J, Melin P, Castillo O (2018) A new approach for time series prediction using ensembles of IT2FNN models with optimization of fuzzy integrators. Int J Fuzzy Syst 20(3):701–728
Yang S, Liu J (2018) Time series forecasting based on high-order fuzzy cognitive maps and wavelet transform. IEEE Trans Fuzzy Syst. https://doi.org/10.1109/TFUZZ.2018.2831640
Waheeb W, Ghazali R, Hussain AJ (2018) Dynamic ridge polynomial neural network with Lyapunov function for time series forecasting. Appl Intell 48(7):1721–1738
Acknowledgements
This work was supported in part by the National Natural Science Foundation of China under Grants 61973070, 61433004, and 61627809, and in part by SAPI Fundamental Research Funds under Grant 2018ZCX22, and in part by the Fundamental Research Funds for the Central Universities under Grant N160406002.
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Yao, X., Wang, Z. Fractional Order Echo State Network for Time Series Prediction. Neural Process Lett 52, 603–614 (2020). https://doi.org/10.1007/s11063-020-10267-y
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11063-020-10267-y