Daily Energy Price Forecasting Using a Polynomial NARMAX Model

  • Catherine McHughEmail author
  • Sonya Coleman
  • Dermot Kerr
  • Daniel McGlynn
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 840)


Energy prices are not easy to forecast due to nonlinearity from seasonal trends. In this paper a Nonlinear AutoRegressive Moving Average model with eXogenous input (NARMAX model) is created using nonlinear energy price data. To investigate if a short-term forecasting model is capable of predicting energy prices a model was developed using daily data from 2017 over a period of five weeks: observing 1 input lag prediction up to 12 input lag prediction for low-order polynomials (linear, quadratic, and cubic). Various input factors were explored (energy demand and previous price) with different combinations to observe which factors, if any, had an impact on the current price prediction. The results show that the generated NARMAX model is good at describing the input-output relationship of energy prices. The model works best with a low-order input regression parameter and linear polynomial degree. It was also noted that including energy demand as an input factor slightly improves the model validation results suggesting that there is a relationship between demand and energy prices.


NARMAX modelling Energy price forecasting Polynomial Machine learning 



This work was funded via DfE CAST scholarship in collaboration with Click Energy.


  1. 1.
    Mosbah, H., El-Hawary, M.: Hourly electricity price forecasting for the next month using multilayer neural network. Can. J. Electr. Comput. Eng. 39, 283–291 (2016). Scholar
  2. 2.
    Gupta, S., Mohanta, S., Chakraborty, M., Ghosh, S.: Quantum machine learning-using quantum computation in artificial intelligence and deep neural networks quantum, pp. 268–274 (2017)Google Scholar
  3. 3.
    Acuna, G., Ramirez, C., Curilem, M.: Comparing NARX and NARMAX models using ANN and SVM for cash demand forecasting for ATM. In: Proceedings of International Joint Conference on Neural Networks, pp. 10–15 (2012).
  4. 4.
    Pandey, N., Upadhyay, K.G.: Different price forecasting techniques and their application in deregulated electricity market : a comprehensive study. In: International Conference on Emerging Trends in Electrical Electronics & Sustainable Energy Systems (ICETEESES), pp. 1–4 (2016).
  5. 5.
    Amjady, N., Hemmati, M.: Energy price forecasting: problems and proposals for such predictions (2006)Google Scholar
  6. 6.
    Vijayalakshmi, S., Girish, G.P.: Artificial neural networks for spot electricity price forecasting: a review. Int. J. Energy Econ. Policy. 5, 1092–1097 (2015)Google Scholar
  7. 7.
    Gao, G., Lo, K., Fan, F.: Comparison of ARIMA and ANN models used in electricity price forecasting for power market. Energy Power Eng. 9, 120–126 (2017). Scholar
  8. 8.
    Georgilakis, P.S.: Artificial intelligence solution to electricity price forecasting problem. Appl. Artif. Intell. 21, 707–727 (2007). Scholar
  9. 9.
    Ghalehkhondabi, I., Ardjmand, E., Weckman, G.R., Young, W.A.: An overview of energy demand forecasting methods published in 2005–2015. Energy Syst. 8, 411–447 (2017). Scholar
  10. 10.
    Li, P., Arci, F., Reilly, J., Curran, K., Belatreche, A., Shynkevich, Y.: Predicting short-term wholesale prices on the Irish single electricity market with artificial neural networks. In: 2017 28th Irish Signals System Conference, ISSC 2017 (2017).
  11. 11.
    Green, A.: Machine learning in energy - part two. Accessed 21 Dec 2017
  12. 12.
    Severiano, C.A., Silva, P.C.L., Sadaei, H.J., Guimaraes, F.G.: Very short-term solar forecasting using fuzzy time series. In: 2017 IEEE International Conference on Fuzzy System, pp. 1–6 (2017).
  13. 13.
    Korenberg, M., Billings, S.A., Liu, Y.P.: An orthogonal parameter estimation algorithm for nonlinear stochastic systems. Acse report 307 (1987)Google Scholar
  14. 14.
    Nehmzow, U.: Robot Behaviour: Design, Description, Analysis and Modelling, pp. 169–171. Springer (2009)Google Scholar
  15. 15.
    Pagano, D.J., Filho, V.D., Plucenio, A.: Identification of polinomial narmax models for an oil well operating by continuous gas-lift. IFAC Proc. 39, 1113–1118 (2006). Scholar
  16. 16.
    Zito, G., Landau, I.D.: A methodology for identification of narmax models applied to diesel engines. IFAC Proc. 16, 374–379 (2005). Scholar
  17. 17.
    Nepomuceno, E.G., Martins, S.A.M.: A lower bound error for free-run simulation of the polynomial NARMAX. Syst. Sci. Control Eng. 4, 50–58 (2016). Scholar
  18. 18.
    Pearson, R.K.: Nonlinear input/output modelling. J. Process Control 5, 197–211 (1995). Scholar
  19. 19.
    Warnes, M.R., Glasseyfl, J., Montague, G.A., Kara, B.: On Data-Based Modelling Techniques for Fermentation Processes. Process Biochem. 31, 147–155 (1996)CrossRefGoogle Scholar
  20. 20.
    Billing, S.A., Voon, W.S.F.: Correlation based model validity tests for nonlinear models. Acse report 285 (1985)Google Scholar
  21. 21.
    Billings, S.A., Fadzil, M.B.: The practical identification of systems with nonlinearities. IFAC Proc. 18, 155–160 (1985). Scholar
  22. 22.
    Nordpool: N2EX Market Prices. Accessed 09 Mar 2018
  23. 23.

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  • Catherine McHugh
    • 1
    Email author
  • Sonya Coleman
    • 1
  • Dermot Kerr
    • 1
  • Daniel McGlynn
    • 2
  1. 1.Intelligent Systems Research Centre (ISRC), School of Computing, Engineering and Intelligent SystemsUlster UniversityLondonderryUK
  2. 2.Click EnergyLondonderryUK

Personalised recommendations