Skip to main content

Advertisement

SpringerLink
Log in

A wavelet-based hybrid neural network for short-term electricity prices forecasting

  • Published:
Artificial Intelligence Review Aims and scope Submit manuscript

Abstract

Forecasting is a very important and difficult task for various economic activities. Despite the great evolution of time series modeling, forecasters are still in the hunt for better strategies to improve mathematical models and come up with more accurate predictions. In this respect, several new models, mixing autoregressive processes to artificial neural networks (ANNs), have recently emerged. This is particularly the case for energy economics, where old forecasting tools are replaced by new hybrid strategies. Along the same lines, this paper aims to define a wavelet-based hybridization, involving nonlinear smooth functions, autoregressive fractionally integrated moving average (ARFIMA) model and feedforward ANNs, for electricity spot prices forecasting. The use of the wavelet decomposition in this model allows to characterize certain patterns of power time series, such as the nonlinear trend and multiple seasonal effects, and to exactly extrapolate them over the time scale. In fact, such patterns have already been pointed out as potential causes of the ANN’s inaccuracy. An ARFIMA–ANN model is then used to forecast the resulting irregular component. In the last stage, the smooth and irregular components are recombined to constitute the forecasted price. We will demonstrate the cost-effectiveness of the proposed method using hourly power prices from the Nord Pool Exchange. The testing time series consists of 52,614 observations and corresponds to the period ranging from 2012 to 2017. The results show that the new method is able to provide better interval forecasting than four benchmark models.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6

Similar content being viewed by others

Notes

  1. An activation function is deterministic and symmetrically nonlinear. The range of the output values of a feedforward model is controlled by N(.). If the output value is not restricted to particular intervals, such as binary or discrete results, then it can simply be set to an identity function.

  2. Denmark, Norway, Sweden and Finland.

References

  • Aladag CH, Egrioglu E, Kadilar C (2012) Improvement in forecasting accuracy using the hybrid model of ARFIMA and feed forward neural network. Am J Intell Syst 2(2):12–17

    Article  Google Scholar 

  • Ben Amor S, Boubaker H, Belkacem L (2018) Forecasting electricity spot price for Nord Pool market with a hybrid \(k\)-factor GARMA–LLWNN model. J Forecast 37(8):832–851

    Article  MathSciNet  MATH  Google Scholar 

  • Ben Mabrouk A, Ben Abdallah N, Dhifaoui Z (2008) Wavelet decomposition and autoregressive model for time series prediction. Appl Math Comput 199(1):334–340

    MathSciNet  MATH  Google Scholar 

  • Chaâbane N (2014) A hybrid ARFIMA and neural network model for electricity price prediction. Int J Electr Power Energy Syst 55:187–194

    Article  Google Scholar 

  • Chaâbane N, Saâdaoui F, Benammou S (2012) Modelling power spot prices in deregulated European energy markets: a dual long memory approach. Glob Bus Econ Rev 14(4):338–361

    Article  Google Scholar 

  • Chen K, Wang C (2007) A hybrid SARIMA and support vector machines in forecasting the production values of the machinery industry in Taiwan. Expert Syst Appl 32(1):254–264

    Article  MathSciNet  Google Scholar 

  • Diongue AK, Guégan D, Vignal B (2009) Forecasting electricity spot market prices with a k-factor GIGARCH process. Appl Energy 86(4):505–510

    Article  Google Scholar 

  • Dragomiretskiy K, Zosso D (2014) Variational mode decomposition. IEEE Trans Signal Process 62(3):531–544

    Article  MathSciNet  MATH  Google Scholar 

  • Fard AK, Akbari-Zadeh MR (2014) A hybrid method based on wavelet, ANN and ARIMA model for short-term load forecasting. J Exp Theor Artif Intell 26(2):167–182

    Article  Google Scholar 

  • Flandrin P (2004) Empirical mode decompositions as data-driven wavelet-like expansions. Int J Wavelets Multiresolut Inf Process 02(04):477–496

    Article  MathSciNet  MATH  Google Scholar 

  • Funahashi K (1989) On the approximate realization of continuous mappings by neural networks. Neural Netw 2(3):183–192

    Article  Google Scholar 

  • Grané A, Veiga H (2010) Wavelet-based detection of outliers in financial time series. Comput Stat Data Anal 54(11):2580–2593

    Article  MathSciNet  MATH  Google Scholar 

  • Granger CWJ, Joyeux R (1980) An introduction to long memory time series models and fractional differencing. J Time Ser Anal 1(1):15–39

    Article  MathSciNet  MATH  Google Scholar 

  • Hamrita MS, Ben Abdallah N, Ben Mabrouk A (2011) A wavelet method coupled with quasi-self-similar stochastic processes for time series approximation. Int J Wavelets Multiresolut Inf Process 9(5):685–711

    Article  MathSciNet  MATH  Google Scholar 

  • Hornik K (1991) Approximation capabilities of multilayer feedforward networks. Neural Netw 4(2):251–257

    Article  MathSciNet  Google Scholar 

  • Huang NE, Shen Z, Long SR, Wu MC, Shin Q, Zheng HH, Yen NC, Tung CC, Liu HH (1998) The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis. Proc Math Phys Eng Sci 454(1971):903–995

    Article  MathSciNet  MATH  Google Scholar 

  • Ismail MT, Audu B, Tumala MM (2016) Comparison of forecasting performance between MODWT-GARCH(1, 1) and MODWT-EGARCH(1, 1) models: evidence from African stock markets. J Finance Data Sci 2(4):254–264

    Article  Google Scholar 

  • Karthikeyan L, Nagesh Kumar D (2013) Predictability of nonstationary time series using wavelet and EMD based ARMA models. J Hydrol 502:103–119

    Article  Google Scholar 

  • Lütkepohl H, Krätzig M (2004) Applied time series econometrics. Cambridge University Press, Cambridge

    Book  MATH  Google Scholar 

  • Mallat S (1999) A wavelet tour of signal processing. Academic Press, New York

    MATH  Google Scholar 

  • Nelson M, Hill T, Remus T, O’Connor M (1999) Time series forecasting using NNs: Should the data be deseasonalized first? J Forecast 18(5):359–367

    Article  Google Scholar 

  • Nowotarski J, Weron R (2018) Recent advances in electricity price forecasting: a review of probabilistic forecasting. Renew Sustain Energy Rev 81(1):1548–1568

    Article  Google Scholar 

  • Pai FP, Lin CS (2005) A hybrid ARIMA and support vector machines model in stock price forecasting. Omega 33(6):497–505

    Article  Google Scholar 

  • Papaioannou GP, Dikaiakos C, Evangelidis GI, Papaioannou P, Georgiadis D (2015) Co-movement analysis of Italian and Greek electricity market wholesale prices by using a wavelet approach. Energies 8(10):11770–11799

    Article  Google Scholar 

  • Percival DB, Walden AT (2000) Wavelet methods for time series analysis. Cambridge University Press, Cambridge

    Book  MATH  Google Scholar 

  • Raviv E, Bouwman KE, van Dijk D (2015) Forecasting day-ahead electricity prices: utilizing hourly prices. Energy Econ 50:227–239

    Article  Google Scholar 

  • Saâdaoui F (2010) Acceleration of the EM algorithm via extrapolation methods: review, comparison and new methods. Comput Stat Data Anal 54(3):750–766

    Article  MathSciNet  MATH  Google Scholar 

  • Saâdaoui F (2013) The price and trading volume dynamics relationship in the EEX power market: a wavelet modeling. Comput Econ 42(1):47–69

    Article  Google Scholar 

  • Saâdaoui F (2017) A seasonal feedforward neural network to forecast the Nord Pool electricity prices. Neural Comput Appl 28(4):835–847

    Article  Google Scholar 

  • Saâdaoui F, Mrad M (2017) Stochastic modelling of the price–volume relationship in electricity markets: evidence from the Nordic energy exchange. Int Trans Electr Energy Syst 27(9):e2362

    Article  Google Scholar 

  • Saâdaoui F, Rabbouch H (2014) A wavelet-based multiscale vector-ANN model to predict comovement of econophysical systems. Expert Syst Appl 41(13):6017–6028

    Article  Google Scholar 

  • Saâdaoui F, Naifar N, Aldohaiman MS (2017) Predictability and co-movement relationships between conventional and Islamic stock market indexes: a multiscale exploration using wavelets. Phys A Stat Mech Appl 482:552–568

    Article  Google Scholar 

  • Sato JR, Morettin PA, Arantes PR, Amaro E Jr (2007) Wavelet based time-varying vector autoregressive modelling. Comput Stat Data Anal 51(12):5847–5866

    Article  MathSciNet  MATH  Google Scholar 

  • Soares LJ, Medeiros MC (2008) Modeling and forecasting short-term electricity load: a comparison of methods with an application to Brazilian data. Int J Forecast 24:630–44

    Article  Google Scholar 

  • Wardana ANI (2016) A comparative study of EMD, EWT and VMD for detecting the oscillation in control loop. In: International seminar on application for technology of information and communication (ISemantic), pp 58–63

  • Weron R (2006) Modeling and forecasting electricity loads and prices: a statistical approach. Wiley, Chichester

    Book  Google Scholar 

  • Weron R (2014) Electricity price forecasting: a review of the state-of-the-art with a look into the future. Int J Forecast 30(4):1030–1081

    Article  Google Scholar 

  • Yang L, Tschernig R (2002) Non- and semiparametric identification of seasonal nonlinear autoregression models. Econ Theory 18(6):1408–1448

    Article  MathSciNet  MATH  Google Scholar 

  • Zhang GP (2003) Time series forecasting using a hybrid ARIMA and neural network model. Neurocomputing 50:159–175

    Article  MATH  Google Scholar 

  • Zhang GP, Qi M (2005) Neural network forecasting for seasonal and trend time series. Eur J Oper Res 160(2):501–514

    Article  MathSciNet  MATH  Google Scholar 

  • Zhu L, Wang Y, Fan Q (2014) MODWT-ARMA model for time series prediction. Appl Math Modell 38(5–6):1859–1865

    Article  MathSciNet  MATH  Google Scholar 

Download references

Acknowledgements

We would like to thank the anonymous reviewers, for their insightful and constructive comments that have greatly contributed to improving the paper, and to the editorial staff for their generous support and assistance during the review process.

Author information

Authors and Affiliations

  1. Department of Statistics, Faculty of Sciences, King Abdulaziz University, P.O. Box 80203, Jeddah, 21589, Saudi Arabia

    Foued Saâdaoui

  2. Laboratoire d’Algèbre, Théorie de Nombres et Analyse Non-linéaire, Faculté des Sciences, University of Monastir, 5019, Monastir, Tunisia

    Foued Saâdaoui & Hana Rabbouch

  3. Institut Supérieur de Gestion de Tunis, Université de Tunis, Cité Bouchoucha, 2000, Tunis, Tunisia

    Hana Rabbouch

Authors
  1. Foued Saâdaoui
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Hana Rabbouch
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Foued Saâdaoui.

Ethics declarations

Conflict of interest

We declare that we are not and shall not be in any situation which could give rise to a conflict of interest in what concerns the publication of this paper.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Saâdaoui, F., Rabbouch, H. A wavelet-based hybrid neural network for short-term electricity prices forecasting. Artif Intell Rev 52, 649–669 (2019). https://doi.org/10.1007/s10462-019-09702-x

Download citation

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10462-019-09702-x

Keywords

Search

Navigation