Application of Neural Networks to Automatic Load Frequency Control

  • Soumyadeep Nag
  • Namitha Philip
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8298)


This paper is intended to present the benefits of the application of artificial neural network to automatic load frequency control. The power system model has been simulated and the conventional PI controller has been replaced by the artificial neural network controller wherein, we have trained the neural controller to behave as a PI controller. The strategy has been successfully tested for both a single area as well as multi area systems using MATLAB/SIMULINK. With the help of a neural controller we have been able to achieve a smaller transient dip as well as faster stabilization of frequency.


Reactive Power Steep Descent Method Marquardt Algorithm Newton Algorithm Area System 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Anderson, C.W., Hittle, D.C., Katz, A.D., Matt Kretchmar, R.: Reinforcement Learning. Neural Networks and PI Control Applied to a Heating Coil, Colorado State University (2000)Google Scholar
  2. 2.
    Douratsos, I., Barry Gomm, J.: Neural Network based model reference Adaptive Control for processes with time delay. International Journal of Information and Systems Sciences 3(1), 161–179 (2007)zbMATHGoogle Scholar
  3. 3.
    Hassan, M.Y., Kothapalli, G.: Comparison Between Neural Network Based PI and PID Controllers. In: 2010 7th International Multi-Conference on Systems, Signals and Devices (2010)Google Scholar
  4. 4.
    Godjevac, J.: Comparitive study of fuuzy control, neural network control and neuro-fuzzy control, Swiss Federal Institute of Technology, Technical Report no. 103/95 (February 1995)Google Scholar
  5. 5.
    Usman, A., Divakar, B.P.: A Simulation Study of Load Frequency Control of Single and Two Area Systems, Department of Electrical and Electronics Engineering, vol. 3, pp. 161–179. Reva Institute of Technology and Management (2007)Google Scholar
  6. 6.
    Levenberg, K.: A method for the solution of certain problems in least squares. Quarterly of Applied Mathematics 5, 164–168 (1944)MathSciNetGoogle Scholar
  7. 7.
    Marquardt, D.: An algorithm for least-squares estimation of nonlinear parameters. SIAM Journal on Applied Mathematics 11(2), 431–441 (1963)CrossRefzbMATHMathSciNetGoogle Scholar
  8. 8.
    Rumelhart, D.E., Hinton, G.E., Williams, R.J.: Learning representations by back-propagating errors. Nature 323, 533–536 (1986)CrossRefGoogle Scholar
  9. 9.
    Wilamowski, B.M., Torvik, L.: Modification of gradient computation in the back-propagation algorithm. In: Artificial Neural Networks in Engineering (ANNIE 1993), November 14-17, St. Louis, MO (1993)Google Scholar
  10. 10.
    Andersen, T.J., Wilamowski, B.M.: A modified regression algorithm for fast one layer neural network training. In: World Congress of Neural Networks, Washington, DC, July 17-21, vol. 1, pp. 687–690 (1995)Google Scholar
  11. 11.
    Wilamowski, B.M.: Neural networks and fuzzy systems. In: Chaps. 124.1 to 124.8 in The ElectronicHandbook, pp. 1893–1914. CRC Press, Boca Raton (1996)Google Scholar
  12. 12.
    Wilamowski, B.M., Chen, Y., Malinowski, A.: Efficient algorithm for training neural networks with one hidden layer. In: 1999 International Joint Conference on Neural Networks (IJCNN 1999), Washington, DC, July 10-16, pp. 1725–1728 (1999); #295 Session: 5.1 Google Scholar
  13. 13.
    Wilamowski, B.M.: Neural networks and fuzzy systems. In: Bishop, R.R. (ed.) Mechatronics Handbook, ch. 32, pp. 33-1–32-26. CRC Press, Boca Raton (2002)Google Scholar
  14. 14.
    Wilamowski, B., Hunter, D., Malinowski, A.: Solving parity-n problems with feedforward neural network. In: Proceedings of the IJCNN 2003 International Joint Conference on Neural Networks, Portland, OR, July 20-23, pp. 2546–2551 (2003)Google Scholar
  15. 15.
    Yu, H., Wilamowski, B.M.: C++ implementation of neural networks trainer. In: 13th International Conference on Intelligent Engineering Systems (INES 2009), Barbados, April 16-18 (2009)Google Scholar
  16. 16.
    Wilamowski, B.M.: Neural network architectures and learning algorithms. IEEE Industrial Electronics Magazine 3(4), 56–63 (2009)CrossRefGoogle Scholar
  17. 17.
    Yu, H., Wilamowski, B.M.: C++ implementation of neural networks trainer. In: 13th International Conference on Intelligent Engineering Systems (INES 2009), Barbados, April 16-18 (2009)Google Scholar
  18. 18.
    Osborne, M.R.: Fisher’s method of scoring. International Statistical Review 86, 271–286 (1992)MathSciNetGoogle Scholar
  19. 19.
    Werbos, P.J.: Back-propagation: Past and future. In: Proceedings of International Conference on NeuralNetworks, San Diego, CA, vol. 1, pp. 343–354 (1988)Google Scholar

Copyright information

© Springer International Publishing Switzerland 2013

Authors and Affiliations

  • Soumyadeep Nag
    • 1
  • Namitha Philip
    • 1
  1. 1.Dept. of Electrical and Electronics EngineeringSRM UniversityChennaiIndia

Personalised recommendations