Rayleigh Fading MIMO Channel Prediction Using RNN with Genetic Algorithm

  • G. Routray
  • P. Kanungo
Part of the Communications in Computer and Information Science book series (CCIS, volume 250)


The spectral efficiency and reliability of Multi-Input Multi-Output (MIMO) systems greatly depends on the prediction result of channel state information (CSI), such that the transmitter and/or the receiver have perfect knowledge of CSI. The employment of linear predictors used for narrow-band prediction has produced poor results in prediction of correlation coefficients of the channel in the presence of received data that has undergone non-linear distortions. Hence, one of the potential solutions to this challenge is artificial neural networks (ANN). In this paper we used fully connected recurrent neural network to predict the Rayleigh fading channel coefficients using genetic algorithm based learning, which is compared with split complex real time and fully complex real time based recurrent learning process.


Multi-Input Multi-Output (MIMO) Neural Network Split Complex Real Time Recurrent Learning (SCRTRL) Fully Complex Real Time Recurrent Learning (FCRTRL) Genetic Algorithm (GA) 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Paulraj, A.J., Gore, D.A., Nabar, R.U., Bolcskei, H.: An overview of mimo communication-a key to gigabit wireless. In: Proceeding of the IEEE, vol. 92, pp. 198–218 (February 2004)Google Scholar
  2. 2.
    Potter, C., Venayagamoorthy, G.K., Kosbar, K.: RNN based MIMO channel prediction. Signal Processing 90, 440–450 (2010)CrossRefzbMATHGoogle Scholar
  3. 3.
    Proakis, J.G., Salehi, M.: Digital Communication, 5th edn. Mc Graw Hill (2008)Google Scholar
  4. 4.
    Huang, J., Winters, J.: Sinusoidal modelling and prediction of fast fading processes. In: Global Tel. Conf., pp. 892–897 (November 1998)Google Scholar
  5. 5.
    Andersen, J., Jensen, J., Jensen, S., Frederiksen, F.: Prediction of future fading based on past measurements. In: IEEE Vehicular Technology Conference, pp. 151–155 (1999)Google Scholar
  6. 6.
    Kechriotis, G., Manolakos, E.S.: Training fully recurrent neural networks with complex weights. IEEE trans.on Circuits and System-II:Analog and Digital, Signal Processing, 41(3), 235–238 (1994)CrossRefGoogle Scholar
  7. 7.
    Goh, S.L., Mandic, D.P.: A complex-valued rtrl algorithm for recurrent neural networks. Neural computation 16, 2699–2713 (2004)CrossRefzbMATHGoogle Scholar
  8. 8.
    Sarma, K.K., Mitra, A.: Estimation of MIMO channels using complex time delay fully Recurrent Neural Network. In: 2nd National Conference on Emerging Trends and Applications in Computer Science (NCETACS), March 4-5 (2011)Google Scholar
  9. 9.
    Yoo, T., Goldsmith, A.: Capacity of fading mimo channels with channel estimation error. IEEE Commun. Soc., 808–813 (2004)Google Scholar
  10. 10.
    Yoo, T., Goldsmith, A.: Capacity and power allocation for fading mimo channels with channel estimation error. IEEE Trans. Inform. Theory 52(5), 2203–2214 (2006)MathSciNetCrossRefzbMATHGoogle Scholar
  11. 11.
    Yoo, T., Yoon, E., Goldsmith, A.: Mimo capacity with channel uncertainty: Does feedback help? In: Proceedings of IEEE GlobeCom, pp. 96–100 (2004)Google Scholar
  12. 12.
    Williams, R.J., Zipser, D.A.: A learning algorithm for continually running fully recurrent neural networks. Neural Computation 1(2), 270–280 (1998)CrossRefGoogle Scholar
  13. 13.
    Laung, H., Haykin, S.: The complex backpropagation algorithm. IEEE Trans. on Signal Proc. 3(9), 2101–2104 (1991)CrossRefGoogle Scholar
  14. 14.
    Goldberg, D.E.: Genetic Algorithms in search. Optimization and Machine Learning. Pearson Plc (2011)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2011

Authors and Affiliations

  • G. Routray
    • 1
  • P. Kanungo
    • 1
  1. 1.Department of Electronics and Telecommunication EngineeringC.V. Raman College of EngineeringBhubaneswarIndia

Personalised recommendations