A hierarchical hybrid neural model with time integrators in long-term load forecasting

  • Otávio A. S. Carpinteiro
  • Isaías Lima
  • Edmilson M. Moreira
  • Carlos A. M. Pinheiro
  • Enzo Seraphim
  • J. Vantuil L. Pinto
Original Article


A novel hierarchical hybrid neural model to the problem of long-term load forecasting is proposed in this paper. The neural model is made up of two self-organizing map nets—one on top of the other—and a single-layer perceptron. It has application into domains which require time series analysis. The model is compared to a mutilated architecture of it, and to a multilayer perceptron. The hierarchical, the mutilated, and the multilayer perceptron models are trained and assessed on load data extracted from a North-American electric utility. They are required to predict either once every week or once every month the electric peak-load during the next two years. The results from the experiments show that the performance of HHNM on long-term load forecasts is better than that of the mutilated model, and much better than that of the MLP model.


Neural networks Time-series forecasting Long-term electrical load forecasting 



This research is supported by CNPq, Brazil.


  1. 1.
    Makridakis S, Hibon M (2000) The M3-Competition: results, conclusions and implications. Int J Forecast 16:451–476CrossRefGoogle Scholar
  2. 2.
    Kangas J (1994) On the analysis of pattern sequences by self-organizing maps. Ph.D. thesis, Laboratory of Computer and Information Science, Helsinki University of Technology, Rakentajanaukio 2 C, SF-02150, FinlandGoogle Scholar
  3. 3.
    Chappell GJ, Taylor JG (1993) The temporal Kohonen map. Neural Netw 6:441–445CrossRefGoogle Scholar
  4. 4.
    Barreto GA, Araújo AFR (2001) Time in self-organizing maps: an overview of models. Int J Comput Res Spec Issue Neural Netw Past Present Future 10(2):139–179Google Scholar
  5. 5.
    Kremer SC (2001) Spatio-temporal connectionist networks: a taxonomy and review. Neural Comput 13(2):249–306MATHCrossRefGoogle Scholar
  6. 6.
    Barreto GA, Araújo AFR, Kremer SC (2003) A taxonomy for spatiotemporal connectionist networks revisited: the unsupervised case. Neural Comput 15(6):1255–1320MATHCrossRefGoogle Scholar
  7. 7.
    Papalexopoulos A, Hao S, Peng T (1994) An implementation of a neural network based load forecasting model for the EMS. IEEE Trans Power Syst 9(4):1956–1962CrossRefGoogle Scholar
  8. 8.
    Bakirtzis A, Petridis V, Klartzis S, Alexiadis M, Maissis A (1996) A neural network short-term load forecasting model for the Greek power system. IEEE Trans Power Syst 11(2):858–863CrossRefGoogle Scholar
  9. 9.
    Khotanzad A, Afkhami-Rohani R, Maratukulam D (1998) ANNSTLF—artificial neural network short-term load forecaster—generation three. IEEE Trans Power Syst 13(4):1413–1422CrossRefGoogle Scholar
  10. 10.
    Hippert H, Pedreira C, Souza R (2001) Neural networks for short-term load forecasting: a review and evaluation. IEEE Trans Power Syst 16(1):44–55CrossRefGoogle Scholar
  11. 11.
    Kermanshahi B (1998) Recurrent neural network for forecasting next 10 years load of nine Japanese utilities. Neurocomputing 23:125–133CrossRefGoogle Scholar
  12. 12.
    Kohonen T (2001) Self-organizing maps, 3rd edn. Springer, BerlinMATHGoogle Scholar
  13. 13.
    Galván IM, Isasi P (2001) Multi-step learning rule for recurrent neural models: an application to time series forecasting. Neural Process Lett 13:115–133MATHCrossRefGoogle Scholar
  14. 14.
    Carpinteiro OAS, Leme RC, Souza ACZ, Filho PSQ (2005) A hierarchical hybrid neural model with time integrators in long-term peak-load forecasting. In: International joint conference on neural networks (IJCNN), Montréal, Canada, August 2005Google Scholar
  15. 15.
    Lo Z, Bavarian B (1991) Improved rate of convergence in Kohonen neural network. In: Proceedings of the international joint conference on neural networks, vol 2, pp 201–206, 8–12 JulyGoogle Scholar
  16. 16.
    Lo Z, Fujita M, Bavarian B (1991) Analysis of neighborhood interaction in Kohonen neural networks. In: Proceedings of the fifth international parallel processing symposium, pp 246–249, April 1991Google Scholar
  17. 17.
    Widrow G, Hoff ME (1960) Adaptive switching circuits. Institute of Radio Engineers, Western Electronic Show and Convention, Convention Record, Part 4Google Scholar
  18. 18.
    Sutton RS, Barto AG (1981) Toward a modern theory of adaptive networks: expectation and prediction. Psychol Rev 88:135–170CrossRefGoogle Scholar
  19. 19.
    El-Sharkawi MA (2002) Internet web page http://www.ee.washington.edu/class/559/2002spr/

Copyright information

© Springer-Verlag London Limited 2009

Authors and Affiliations

  • Otávio A. S. Carpinteiro
    • 1
  • Isaías Lima
    • 1
  • Edmilson M. Moreira
    • 1
  • Carlos A. M. Pinheiro
    • 1
  • Enzo Seraphim
    • 1
  • J. Vantuil L. Pinto
    • 1
  1. 1.Research Group on Systems and Computer EngineeringFederal University of ItajubáItajubáBrazil

Personalised recommendations