Skip to main content

Advertisement

SpringerLink
Log in

A hybrid approach to model and forecast the electricity consumption by NeuroWavelet and ARIMAX-GARCH models

  • Original Article
  • Published:
Energy Efficiency Aims and scope Submit manuscript

Abstract

Today, electrical energy plays a major role in production and consumption and is of special importance in economic decision-making process. Being aware of electrical energy demand for each period is necessary to correct planning. Therefore, the forecasting of electricity consumption is important among several economic sections. Besides the traditional models, in this paper, we offer a hybrid forecast approach that combines the adaptive wavelet neural network with the ARIMA-GARCH family models and uses the effective exogenous variables on electricity consumption. Based on this approach, two hybrid models are proposed. To assess the ability of the proposed models, we forecasted the daily electricity consumption by the hybrid and benchmark models for 60 days ahead in two separate seasons (summer and winter). The empirical results showed that the proposed models have more prediction accuracy compared with the other benchmark forecast models including neural network, adaptive wavelet neural network, and ARIMAX-GARCH family 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
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12

Similar content being viewed by others

Notes

  1. A stationary process has the property that the mean, variance, and autocorrelation structure do not change over time. Most statistical forecasting methods are based on the assumption that the time series can be rendered approximately stationary through the use of mathematical transformations. Non-stationary data is, conceptually, the data that is very difficult to model because the estimate of the mean (and sometimes the variance) will be changing.

  2. PJM is a regional transmission organization (RTO) in the Eastern United States that operates one of the world’s largest competitive wholesale electricity markets.

  3. The leverage effect means the phenomenon of a correlation of past returns with future volatility. This correlation is negative, which means the variance of EC with a decrease in EC.

  4. The feedback effect is based on the following dependence: if the volatility has its EC, the anticipated increase in volatility will increase in EC.

  5. Including holidays, special events, promotional activities, and system failures. We take it into account in the form of a binary dummy variable. The binary nature of the dummy contains the information about whether an event is occurring (1) or not (0).

  6. Include:

    - The checking of stationary or non-stationary and transforming the data, if necessary;

    - The identification of a suitable ARMA model;

    - The estimation of the parameters of the chosen model;

    - The diagnostic checking of the model’s adequacy.

  7. Considering the lack of integration order (I), the ARIMA models were turned to ARMA.

  8. These include 7 days a week, 12 months a year, temperature (min, average, and max), and special days.

References

  • Abedinia, O., & Amjady, N. (2015). Day-ahead price forecasting of electricity markets by a new hybrid forecast method. Modeling and Simulation in Electrical and Electronics Engineering, 1(1), 1–7.

    Google Scholar 

  • Amjady, N., & Keynia, F. (2008). Day ahead price forecasting of electricity markets by a mixed data model and hybrid forecast method. International Journal of Electrical Power & Energy Systems, 30(9), 533–546.

    Article  Google Scholar 

  • Bashir, Z. A., & El-Hawary, M. E. (2009). Applying wavelets to short-term load forecasting using PSO-based neural networks. IEEE Transactions on Power Systems, 24(1), 20–27.

    Article  Google Scholar 

  • Bollerslev, T. (1986). Generalized autoregressive conditional heteroskedasticity. Journal of Econometrics, 31(3), 307–327.

    Article  MathSciNet  MATH  Google Scholar 

  • Bouzari, H., Šramek, M., Mistelbauer, G., & Bouzari, E. (2011). Robust adaptive wavelet neural network control of Buck converters. In Recent advances in robust control-novel approaches and design methods. IntechOpen.

  • Box, G. E., & Jenkins, G. M. (1976). Time series analysis: forecasting and control, revised ed. Holden-Day.

  • Chaâbane, N. (2014). A hybrid ARFIMA and neural network model for electricity price prediction. International Journal of Electrical Power & Energy Systems, 55, 187–194.

    Article  Google Scholar 

  • Chand, S., Kamal, S., & Ali, I. (2012). Modelling and volatility analysis of share prices using ARCH and GARCH models. World Applied Sciences Journal, 19(1), 77–82.

    Google Scholar 

  • Chen, Y., Luh, P. B., Guan, C., Zhao, Y., Michel, L. D., Coolbeth, M. A., … & Rourke, S. J. (2010). Short-term load forecasting: similar day-based wavelet neural networks. IEEE Transactions on Power Systems, 25(1), 322–330.

  • Chen, H., Wan, Q., & Wang, Y. (2014). Refined Diebold-Mariano test methods for the evaluation of wind power forecasting models. Energies, 7(7), 4185–4198.

    Article  Google Scholar 

  • Conejo, A. J., Plazas, M. A., Espinola, R., & Molina, A. B. (2005). Day-ahead electricity price forecasting using the wavelet transform and ARIMA models. IEEE Transactions on Power Systems, 20(2), 1035–1042.

    Article  Google Scholar 

  • Ding, S., Hipel, K. W., & Dang, Y. G. (2018). Forecasting China’s electricity consumption using a new grey prediction model. Energy, 149, 314–328.

    Article  Google Scholar 

  • Engle, R. F. (1982). Autoregressive conditional heteroscedasticity with estimates of the variance of United Kingdom inflation. Econometrica: Journal of the Econometric Society, 50, 987–1007.

    Article  MathSciNet  MATH  Google Scholar 

  • Erdogdu, E. (2010). Natural gas demand in Turkey. Applied Energy, 87(1), 211–219.

    Article  Google Scholar 

  • Hickey, E., Loomis, D. G., & Mohammadi, H. (2012). Forecasting hourly electricity prices using ARMAX–GARCH models: An application to MISO hubs. Energy Economics, 34(1), 307–315.

    Article  Google Scholar 

  • Hong, T. (2010). Short term electric load forecasting.

  • Hong, T., Pinson, P., & Fan, S. (2014). Global energy forecasting competition 2012.

  • Jarque, C. M., & Bera, A. K. (1980). Efficient tests for normality, homoscedasticity and serial independence of regression residuals. Economics Letters, 6(3), 255–259.

    Article  MathSciNet  Google Scholar 

  • Kavaklioglu, K., Ceylan, H., Ozturk, H. K., & Canyurt, O. E. (2009). Modeling and prediction of Turkey’s electricity consumption using artificial neural networks. Energy Conversion and Management, 50(11), 2719–2727.

    Article  Google Scholar 

  • Kim, K. H., Park, J. K., Hwang, K. J., & Kim, S. H. (1995). Implementation of hybrid short-term load forecasting system using artificial neural networks and fuzzy expert systems. IEEE Transactions on Power Systems, 10(3), 1534–1539.

    Article  Google Scholar 

  • Kristjanpoller, W., & Minutolo, M. C. (2018). A hybrid volatility forecasting framework integrating GARCH, artificial neural network, technical analysis and principal components analysis. Expert Systems with Applications, 109, 1–11.

    Article  Google Scholar 

  • Liu, H., & Shi, J. (2013). Applying ARMA–GARCH approaches to forecasting short-term electricity prices. Energy Economics, 37, 152–166.

    Article  MathSciNet  Google Scholar 

  • Mandal, P., Haque, A. U., Meng, J., Srivastava, A. K., & Martinez, R. (2013). A novel hybrid approach using wavelet, firefly algorithm, and fuzzy ARTMAP for day-ahead electricity price forecasting. IEEE Transactions on Power Systems, 28(2), 1041–1051.

    Article  Google Scholar 

  • May, R., Dandy, G., & Maier, H. (2011). Review of input variable selection methods for artificial neural networks. In Artificial neural networks-methodological advances and biomedical applications. InTech.

  • Morales-Acevedo, A. (2014). Forecasting future energy demand: electrical energy in Mexico as an example case. Energy Procedia, 57, 782–790.

    Article  Google Scholar 

  • Nury, A. H., Hasan, K., & Alam, M. J. B. (2017). Comparative study of wavelet-ARIMA and wavelet-ANN models for temperature time series data in northeastern Bangladesh. Journal of King Saud University-Science, 29(1), 47–61.

    Article  Google Scholar 

  • Pindoriya, N. M., Singh, S. N., & Singh, S. K. (2008). An adaptive wavelet neural network-based energy price forecasting in electricity markets. IEEE Transactions on Power Systems, 23(3), 1423–1432.

    Article  Google Scholar 

  • Pindoriya, N. M., Singh, S. N., & Singh, S. K. (2010). Forecasting of short-term electric load using application of wavelets with feed-forward neural networks. International Journal of Emerging Electric Power Systems, 11(1).

  • Rahman, S., & Hazim, O. (1993). A generalized knowledge-based short-term load-forecasting technique. IEEE Transactions on Power Systems, 8(2), 508–514.

    Article  Google Scholar 

  • Rana, M., & Koprinska, I. (2016). Forecasting electricity load with advanced wavelet neural networks. Neurocomputing, 182, 118–132.

    Article  Google Scholar 

  • Reis, A. R., & Da Silva, A. A. (2005). Feature extraction via multiresolution analysis for short-term load forecasting. IEEE Transactions on Power Systems, 20(1), 189–198.

    Article  Google Scholar 

  • Reston Filho, J. C., Affonso, C. D. M., & de Oliveira, R. C. (2014). Energy price prediction multi-step ahead using hybrid model in the Brazilian market. Electric Power Systems Research, 117, 115–122.

    Article  Google Scholar 

  • Sánchez, J. M. B., Lugilde, D. N., de Linares Fernández, C., de la Guardia, C. D., & Sánchez, F. A. (2007). Forecasting airborne pollen concentration time series with neural and neuro-fuzzy models. Expert Systems with Applications, 32(4), 1218–1225.

    Article  Google Scholar 

  • Schwarz, G. (1978). Estimating the dimension of a model. The Annals of Statistics, 6(2), 461–464. https://doi.org/10.1214/aos/1176344136.

    Article  MathSciNet  MATH  Google Scholar 

  • Shafie-Khah, M., Moghaddam, M. P., & Sheikh-El-Eslami, M. K. (2011). Price forecasting of day-ahead electricity markets using a hybrid forecast method. Energy Conversion and Management, 52(5), 2165–2169.

    Article  Google Scholar 

  • Sumer, K. K., Goktas, O., & Hepsag, A. (2009). The application of seasonal latent variable in forecasting electricity demand as an alternative method. Energy Policy, 37(4), 1317–1322.

    Article  Google Scholar 

  • Szoplik, J. (2015). Forecasting of natural gas consumption with artificial neural networks. Energy, 85, 208–220.

    Article  Google Scholar 

  • Tan, Z., Zhang, J., Wang, J., & Xu, J. (2010). Day-ahead electricity price forecasting using wavelet transform combined with ARIMA and GARCH models. Applied Energy, 87(11), 3606–3610.

    Article  Google Scholar 

  • Thomas, S., & Mitchell, H. (2005). GARCH modeling of high-frequency volatility in Australia’s National Electricity Market. System, 1–39.

  • Valenzuela, O., Rojas, I., Rojas, F., Pomares, H., Herrera, L. J., Guillén, A., … & Pasadas, M. (2008). Hybridization of intelligent techniques and ARIMA models for time series prediction. Fuzzy Sets and Systems, 159(7), 821–845.

  • Wu, L., & Shahidehpour, M. (2010). A hybrid model for day-ahead price forecasting. IEEE Transactions on Power Systems, 25(3), 1519–1530.

    Article  Google Scholar 

  • Yu, H., & Wilamowski, B. M. (2011). Chapter 12. In Levenberg–Marquardt training industrial electronics handbook (pp. 12–11). CRC.

  • Zhai, M.-Y. (2015). A new method for short-term load forecasting based on fractal interpretation and wavelet analysis. International Journal of Electrical Power & Energy Systems, 69, 241–245.

    Article  Google Scholar 

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

    Article  MATH  Google Scholar 

  • Zhang, J., Tan, Z., & Yang, S. (2012). Day-ahead electricity price forecasting by a new hybrid method. Computers & Industrial Engineering, 63(3), 695–701.

    Article  Google Scholar 

  • Zolfaghari, M., & Sahabi, B. (2017). Impact of foreign exchange rate on oil companies risk in stock market: a Markov-switching approach. Journal of Computational and Applied Mathematics, 317, 274–289.

    Article  MathSciNet  MATH  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Faculty of Management and Economics, Tarbiat Modares University, Tehran, Iran

    Mehdi Zolfaghari & Bahram Sahabi

Authors
  1. Mehdi Zolfaghari
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Bahram Sahabi
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Mehdi Zolfaghari.

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

Zolfaghari, M., Sahabi, B. A hybrid approach to model and forecast the electricity consumption by NeuroWavelet and ARIMAX-GARCH models. Energy Efficiency 12, 2099–2122 (2019). https://doi.org/10.1007/s12053-019-09800-3

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s12053-019-09800-3

Keywords

Search

Navigation