Abstract
Improving time series forecasting accuracy is an important work for decision makers. A single model applied on a data series may not obtain satisfactory prediction accuracy. Both theoretical and empirical findings have indicated that integration of linear model and nonlinear model may provide more accurate prediction than an individual linear or nonlinear model. This paper presents a hybrid modeling approach that combines a linear autoregressive (AR) model and a nonlinear deep belief network-based autoregressive (DBN-AR) model for time series forecasting. The proposed modeling approach first applies an AR model to fit time series data, and the error between the original date and the AR model forecast data as a nonlinear component is considered, and then the error is modeled by a DBN-AR model. DBaN-AR model is a modeling method for nonlinear time series, which uses a set of deep belief networks to approximate the state-dependent functional coefficients of state dependent auto-regressive model. The proposed hybrid model can overcome limitation of an individual model and obtain more general and more accurate forecasting result than some existing hybrid models. The experiment results demonstrate that the MSE of modeling residuals using the proposed hybrid model is largely reduced compared with the results of some single prediction models and some hybrid models for one-step-ahead and multistep-ahead forecast.
Similar content being viewed by others
References
Khashei M, Bijari M (2011) A novel hybridization of artificial neural networks and ARIMA models for time series forecasting. Appl Soft Comput 11(2):2664–2675
Khashei M, Bijari M, Ardali GAR (2009) Improvement of auto-regressive integrated moving average models using fuzzy logic and artificial neural networks (ANNs). Neurocomputing 72(4–6):956–967
Wang D, Guo H, Luo H, Grunder O, Lin Y (2017) Multi-step-ahead electricity price forecasting using a hybrid model based on two-layer decomposition technique and BP neural network optimized by firefly algorithm. Appl Energy 190:390–407
Lei M, Luan S, Jiang C, Liu H, Yan Z (2009) A review on the forecasting of wind speed and generated power. Renew Sustain Energy Rev 13(4):915–920
Shen S, Shen Y (2016) ARIMA: an applied time series forecasting model for the bovespa stock index. J Comput Commun 5(21):3383–3391
Takeda H, Tamura Y, Sato S (2016) Using the ensemble Kalman filter for electricity load forecasting and analysis. Energy 104:184–198
Bengio Y (2009) Learning deep architectures for AI. Found Trends® Mach Learn 2(1):1–127
Lv Y, Duan Y, Kang W, Li Z, Wang FY (2015) Traffic flow prediction with big data: a deep learning approach. IEEE Trans Intell Transp Syst 16(2):865–873
Hinton GE, Osindero S, Teh YW (2014) A fast learning algorithm for deep belief nets. Neural Comput 18(7):1527–1554
Qin M, Du Z, Du Z (2017) Red tide time series forecasting by combining ARIMA and deep belief network. Knowl-Based Syst 125:39–52
Qiu X, Ren Y, Suganthan PN, Amaratunga GAJ (2017) Empirical mode decomposition based ensemble deep learning for load demand time series forecasting. Appl Soft Comput 54:246–255
Yin Y, Shang P (2016) Forecasting traffic time series with multivariate predicting method. Appl Math Comput 291:266–278
Shen F, Chao J, Zhao J (2015) Forecasting exchange rate using deep belief networks and conjugate gradient method. Neurocomputing 167:243–253
Dong Y, Liu Y, Lian S (2016) Automatic age estimation based on deep learning algorithm. Neurocomputing 187:4–10
Hinton GE, Salakhutdinov RR (2006) Reducing the dimensionality of data with neural networks. Science 313(5786):504
Collobert R, Weston J (2008) A unified architecture for natural language processing: deep neural networks with multitask learning. In: International conference 160–167
Zhou J, Jing S, Gong L (2011) Fine tuning support vector machines for short-term wind speed forecasting. Energy Convers Manag 52(4):1990–1998
Babu CN, Reddy BE (2014) A moving-average filter based hybrid arima–ann model for forecasting time series data. Appl Soft Comput 23(10):27–38
Li S, Wang P, Goel L (2016) A novel wavelet-based ensemble method for short-term load forecasting with hybrid neural networks and feature selection. IEEE Trans Power Syst 31(3):1788–1798
Ardalani-Farsa M, Zolfaghari S (2010) Chaotic time series prediction with residual analysis method using hybrid Elman-NARX neural networks. Neurocomputing 73(13–15):2540–2553
Bai Y, Chen Z, Xie J, Li C (2016) Daily reservoir inflow forecasting using multiscale deep feature learning with hybrid models. J Hydrol 532:193–206
Zhang GP (2003) Time series forecasting using a hybrid ARIMA and neural network model. Neurocomputing 50(1):159–175
Priestley MB (1980) State-dependent models: a general approach to non-linear time series analysis. J Time 1(1):47–71
Vesin J (1993) An amplitude-dependent autoregressive signal model based on a radial basis functions expansion. In: Proc. IEEE Int. Conf. on acoustics, speech and signal processing, ICASSP"93, Minneapolis, USA, 3
Shi Z, Tamura Y, Ozaki T (1999) Nonlinear time series modelling with the radial basis function-based state-dependent autoregressive model. Int J Syst Sci 30(7):717–727
Peng H, Ozaki T, Hagganozaki V, Toyoda Y (2003) A parameter optimization method for radial basis function type models. IEEE Trans Neural Networks 14(2):432–438
Gan M, Peng H, Peng X, Chen X, Inoussa G (2010) A locally linear RBF network-based state-dependent AR model for nonlinear time series modeling. Inf Sci 180(22):4370–4383
Gan M, Peng H, Chen L (2012) A global–local optimization approach to parameter estimation of RBF-type models. Inf Sci 197:144–160
Zhou F, Peng H, Qin Y, Zeng X, Tian X, Xu W (2017) A RBF-ARX model-based robust MPC for tracking control without steady state knowledge. J Process Control 51:42–54
Zhou F, Peng H, Qin Y, Zeng X, Xie W, Wu J (2015) RBF-ARX model-based MPC strategies with application to a water tank system. J Process Control 34:97–116
Xu W, Peng H, Zeng X, Zhou F, Tian X, Peng X (2019) Deep belief network-based AR model for nonlinear time series forecasting. Appl Soft Comput 77:605–621
Chen GY, Gan M, Chen CLP, Li HX (2019) A regularized variable projection algorithm for separable nonlinear least squares problems. IEEE Trans Autom Control 64(2):526–537
Gan M, Chen CLP, Li HX, Chen L (2015) Gradient radial basis function based varying-coefficient autoregressive model for nonlinear and nonstationary time series. IEEE Signal Process Lett 22(7):809–812
Gan M, Chen CLP, Chen GY, Chen L (2018) On some separated algorithms for separable nonlinear squares problems. IEEE Trans Cybern 48(10):2866–2874
SIDC (World Data Center for the Sunspot Index). http://side.oma.be/index.php3
AEMO, (2013) Australian energy market operator. http://www.aemo.com.au/
Akaike H (1969) Fitting autoregressive models for prediction. Ann Inst Stat Math 21(1):243–247
Jang RJS, Gulley N (2000) Fuzzy logic toolbox user’s guide. The Math Works Inc, Natick, MA
Sello S (2001) Solar cycle forecasting: a nonlinear dynamics approach. Astron Astrophys 377(1):312–320
Gholipour A, Araabi BN, Lucas C (2006) Predicting chaotic time series using neural and neurofuzzy models: a comparative study. Neural Process Lett 24(3):217–239
Wang D, Luo H, Grunder O, Lin Y, Guo H (2017) Multi-step ahead electricity price forecasting using a hybrid model based on two layer decomposition technique an BP neural network optimized by firefly algorithm. Appl Energy 190:390–407
Acknowledgements
The authors would like to thank the editors and referees for their valuable comments and suggestions, which substantially improved the original manuscript. This research was supported by the National Natural Science Foundation of China (61773402, 51575167, 61540037, and 71271215), the key projects of natural science research in colleges and universities of Anhui Province (Grant No. KJ2020A0508), and the Anhui Provincial Natural Science Foundation (2008085MF197, 1908085MF195).
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.
Appendix A
Appendix A
1.1 Nomenclature
- DBN:
-
Deep belief network
- SD-AR:
-
State dependent auto-regressive
- DBN-AR:
-
Deep belief network-based autoregressive
- AR:
-
Auto-regressive
- AI:
-
Artificial intelligence
- ARMA:
-
Auto-regressive moving average
- ARIMA:
-
Auto-regressive integrated moving average
- ANN:
-
Artificial neural network
- SVM:
-
Support vector machine
- ELM:
-
Extreme learning machine
- DL:
-
Deep learning
- RBM:
-
Restricted boltzmann machines
- NARX:
-
Nonlinear autoregressive model with eXogenous
- RBF:
-
Radial basis function
- LLRBF:
-
Locally linear RBF
- AEMO:
-
Australian energy market operator
- LSM:
-
Least square method
- AIC:
-
Akaike information criteria
- MSE:
-
Mean squared errors
- RMSE:
-
Root mean square error
- NMSE:
-
Normalized mean squared error
- SIDC:
-
World data center for the sunspot index
- AEMO:
-
Australian energy market operator
- VIC:
-
Victoria
Rights and permissions
About this article
Cite this article
Xu, W., Peng, H., Zeng, X. et al. A Hybrid Modeling Method Based on Linear AR and Nonlinear DBN-AR Model for Time Series Forecasting. Neural Process Lett 54, 1–20 (2022). https://doi.org/10.1007/s11063-021-10651-2
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11063-021-10651-2