Advertisement

Application of Artificial Neural Network and Empirical Mode Decomposition for Predications of Hourly Values of Active Power Consumption

  • Maja Muftić DedovićEmail author
  • Nedis Dautbašić
  • Adnan Mujezinović
Conference paper
Part of the Lecture Notes in Networks and Systems book series (LNNS, volume 59)

Abstract

The precision of load forecasting is of great importance for power distribution systems planning and management. As load data are highly nonlinear and nonstationary time series, ordinary methods of linear prediction seem insufficient. In this paper, for the active power consumption forecasting, two methods are used. A method using artificial neural network (ANN) based technique is developed for short-term and mid-term load forecasting of power distribution system. Aiming to increase the accuracy of load prediction, method using artificial neural network and Empirical Mode Decomposition (EMD) technique for short-term and mid-term load forecast is developed. Two cases are used to validate the prediction methods.

Keywords

Load forecast Artificial neural network (ANN) Empirical mode decomposition (EMD) 

References

  1. 1.
    Abu-Shikhah, N., Elkarmi, F., Aloquili, O.: Medium-term electric load forecasting using multivariable linear and non-linear regression. Smart Grid Renew. Energy 2, 126–135 (2011).  https://doi.org/10.4236/sgre.2011.22015. http://www.SciRP.org/journal/sgreCrossRefGoogle Scholar
  2. 2.
    Tuaimah, F.M., Abass, H.M.A.: Short-term electrical load forecasting for iraqi power system based on multiple linear regression method. Int. J. Comput. Appl. 100(1) (2014). ISSN 0975-8887Google Scholar
  3. 3.
    Islam, B.U.: Comparison of conventional and modern load forecasting techniques based on artificial intelligence and expert systems. IJCSI Int. J. Comput. Sci. Issues 8(5), no. 3 (2011)Google Scholar
  4. 4.
    Haykin, S.: Neural Networks: A Comprehensive Foundation, 2nd edn, p. 1104. Williams Publishing House, Jerusalem (2006)Google Scholar
  5. 5.
    Caciotta, M., Giarnetti, S., Leccese, F.: Hybrid neural network system for electric load forecasting of telecommunication station. In: Proceedings of XIX IMEKO World Congress Fundamental and Applied Metrology, Lisbon, Porugal, 6–11 September 2009, pp. 657–661 (2009)Google Scholar
  6. 6.
    Weili, B., Zhigang, L., Quanwei, P., Jian, X.: Research of the load forecasting model based on HHT and combination of ANN. Power Syst. Prot. Control 37(19), 31–35 (2009)Google Scholar
  7. 7.
    Weili, B., Zhigang, L., Qi, W., Dengdeng, Z.: Load forecasting of power system based on HHT. Sichuan Electr. Power Technol. 32(3), 9–13 (2009)Google Scholar
  8. 8.
    Liu, Z.G., Bai, W.L., Chen, G.: A new short-term load forecasting model of power system based on HHT and ANN. In: Lecture Notes in Computer Science, vol. 6064, pp. 448–454 (2010)Google Scholar
  9. 9.
    Kutbatsky, V., Sidorov, D., Spiryaev, V., Tomin, N.: On the neural network approach for forecasting of nonstationary time series on the basis of the Hilbert-Huang transform. Autom. Remote Control 72(7), 1405–1414 (2011)MathSciNetCrossRefGoogle Scholar
  10. 10.
    Kutbatsky, V., Sidorov, D., et al.: Hybrid model for short-term forecasting in electric power system. Int. J. Mach. Learn. Comput. 1(2), 138–147 (2011)CrossRefGoogle Scholar
  11. 11.
    Dedovic, M.M., Avdakovic, S., Turkovic, I., Dautbasic, N., Konjic, T.: Forecasting PM10 concentrations using neural networks and system for improving air quality. In: 2016 XI International Symposium on Telecommunications (BIHTEL), pp. 1–6 (2016)Google Scholar
  12. 12.
    Lee, K.Y., Park, J.H.: Short-term load forecasting using an artificial neural network. Trans. Power Syst. 7(1), 124–132 (1992)CrossRefGoogle Scholar
  13. 13.
    Huang, H.E., Shen, Z., Long, S.R., Wu, M.C., Shih, H.H., Zheng, Q., Yen, N.-C., Tung, C.C., Liu, H.H.: The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis. Proc. R. Soc. Lond. A 454, 903–995 (1998)MathSciNetCrossRefGoogle Scholar
  14. 14.
    Dedovic, M.M., Avdakovic, S., Dautbasic, N.: Impact of air temperature on active and reactive power consumption - Sarajevo case study. Bosanskohercegovačka elektrotehnika (under revision)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  • Maja Muftić Dedović
    • 1
    Email author
  • Nedis Dautbašić
    • 1
  • Adnan Mujezinović
    • 1
  1. 1.Faculty of Electrical EngineeringSarajevoBosnia and Herzegovina

Personalised recommendations