RNN Based MIMO Channel Prediction

  • Chris Potter
Part of the Evolutionary Learning and Optimization book series (ALO, volume 4)


In this work, differential evolution (DE) is combined with particle swarm optimization (PSO) and another evolutionary algorithm (EA) to create a novel hybrid PSO-EA-DEPSO algorithm. The alteration between PSO, PSO-EA, and DEPSO provides additional diversity to counteract premature convergence. This hybrid algorithm is then shown to outperform PSO, PSO-EA, and DEPSO when applied to wireless MIMO channel prediction.


Particle Swarm Optimization Differential Evolution Channel State Information Recurrent Neural Network Channel Estimation Error 
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.
    Telatar, E.: Capacity of multi-antenna gaussian channels. AT&T Bell Laboratories Internal Technical Memorandum (June 1995)Google Scholar
  2. 2.
    Foschini, G., Gans, M.: On limits of wireless communications in a fading environment when using multiple antennas. Wireless Personal Communications 6(3), 311–335 (1998)CrossRefGoogle Scholar
  3. 3.
    Papoulis, A., Pillai, S.: Probability, Random Variables, and Stochastic Processes. McGraw-Hill Science, New York (1990)Google Scholar
  4. 4.
    Huang, J., Winters, J.: Sinusoidal modeling and prediction of fast fading processes. In: Global Telecommunications Conf., Sydney, Australia, November 8-12, pp. 892–897 (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 Conf., Amsterdam, The Netherlands, September 19-22, pp. 151–155 (1999)Google Scholar
  6. 6.
    Duel-Hallen, A., Hu, S., Hallen, H.: Long-range prediction of fading signals: enabling adaptive transmission for mobile radio channels. IEEE Signal Processing Magazine 17(3), 62–75 (2000)CrossRefGoogle Scholar
  7. 7.
    Liu, W., Yang, L.L., Hanzo, L.: Recurrent neural network based narrowband channel prediction. In: IEEE Vehicular Technology Conf., Melbourne, Australia, May 7-10, vol. 5, pp. 2173–2177 (2006)Google Scholar
  8. 8.
    Visweswaran, B., Kiran, T.: Channel prediction based power control in w-cdma systems. In: 1st Int. Conf. 3G Mobile Communications Technologies, London, UK, March 27-29, pp. 41–45 (2000)Google Scholar
  9. 9.
    Gao, X., Tanskanen, J., Ovaska, S.: Comparison of linear and neural network-based power prediction schemes for ds/cdma systems. In: IEEE Vehicular Technology Conf., Atlanta, GA, April 28-May 1, pp. 61–65 (1996)Google Scholar
  10. 10.
    Gao, X., Tanskanen, J., Ovaska, S.: Power prediction in mobile communication systems using an optimal neural network structure. IEEE Trans. Neural Networks 8(6), 1446–1455 (1997)CrossRefGoogle Scholar
  11. 11.
    Cai, X., Zhang, N., Venayagamoorthy, G.K., Wunsch, D.C.: Time series prediction with recurrent neural networks trained by a hybrid pso-ea algorithm. Elsevier J. Neurocomputing 70(13-15), 2342–2353 (2007)CrossRefGoogle Scholar
  12. 12.
    Kennedy, J., Eberhart, R.C.: Particle swarm optimization. In: IEEE Int. Conf. Neural Networks, Perth, WA, November 27 - December 1, vol. 4, pp. 1942–1948 (1995)Google Scholar
  13. 13.
    Kennedy, J., Eberhart, R., Shi, Y.: Swarm Intelligence. Morgan Kaufmann Publishers, San Francisco (2001)Google Scholar
  14. 14.
    Storn, R., Price, K.V.: Differential Evolution - A Simple and Efficient Adaptive Scheme for Global Optimization over Continuous Spaces, Technical Report TR-95-012, International Computer Science Insitute (March 1995)Google Scholar
  15. 15.
    Storn, R., Price, K.V.: Differential evolution-a simple and efficient heuristic for global optimization over continuous spaces. J. Global Optimization 11(4), 341–359 (1997)zbMATHCrossRefMathSciNetGoogle Scholar
  16. 16.
    Mayer, D., Kinghorn, B., Archer, A.: Differential evolution-an easy and efficient evolutionary algorithm for model optimisation. Elsevier J. Agricultural Systems 83(3), 315–328 (2005)CrossRefGoogle Scholar
  17. 17.
    Price, K.V., Storn, R.M., Lampinen, J.A.: Differential Evolution: a Practical Approach to Global Optimization. Springer, Berlin (2005)zbMATHGoogle Scholar
  18. 18.
    Qing, A.: Differential Evolution: Fundamentals and Applications in Electrical Engineering. John Wiley & IEEE, New York (2009)Google Scholar
  19. 19.
    Xu, R., Venayagamoorthy, G.K., Wunsch, D.C.: Modeling of gene regulatory networks with hybrid differential evolution and particle swarm optimization. Elsevier J. Neural Networks 21(8), 917–927 (2007)CrossRefGoogle Scholar
  20. 20.
    Zheng, Y., Xiao, C.: Improved models for the generation of multiple uncorrelated Rayleigh fading waveforms. IEEE Communications Letters 6(6), 256–258 (2002)CrossRefGoogle Scholar
  21. 21.
    Shiu, D., Goschini, G., Gans, M., Kahn, J.: Fading correlation and its effect on the capacity of multi-element antenna systems. IEEE Trans. Communications 48(3), 502–513 (2000)CrossRefGoogle Scholar
  22. 22.
    van Zelst, A., Hammerschmidt, J.: A single coefficient spatial correlation model for multiple-input multiple-output (mimo) radio channels. In: General Assembly Int. Union Radio Science, Maastricht, The Netherlands, August 17-24 (2002)Google Scholar
  23. 23.
    Ortega, J.M.: Matrix Theory-A Second Course. Plenum, New York (1987)zbMATHGoogle Scholar
  24. 24.
    Yoo, T., Goldsmith, A.: Capacity of fading mimo channels with channel estimation error. In: IEEE Int. Conf. Communications, Paris, France, June 20-24, vol. 2, pp. 808–813 (2004)Google Scholar
  25. 25.
    Yoo, T., Yoon, E., Goldsmith, A.: Mimo capacity with channel uncertainty: Does feedback help? In: IEEE Global Telecommunications Conf., Dallas, TX, November 29-December 3, vol. 1, pp. 96–100 (2004)Google Scholar
  26. 26.
    Yoo, T., Goldsmith, A.: Capacity and power allocation for fading mimo channels with channel estimation error. IEEE Trans. Information Theory 52(5), 2203–2214 (2006)CrossRefMathSciNetGoogle Scholar
  27. 27.
    Proakis, J.: Digital Communications. McGraw-Hill, New York (1995)Google Scholar
  28. 28.
    Rappaport, T.S.: Wireless Communications: Principles and Practice. Prentice Hall, Upper Saddle River (2002)Google Scholar
  29. 29.
    Rice, S.: Statistical properties of a sine wave plus random noise. Bell System Technical J. 27(1), 109–157 (1948)MathSciNetGoogle Scholar
  30. 30.
    Sampath, A., Holtzman, J.: Estimation of maximum doppler frequency for handoff decisions. In: IEEE Vehicular Technology Conf., Secaucus, NJ, May 18-20, pp. 859–862 (1993)Google Scholar
  31. 31.
    Bitran, Y.: Broadband data, video, voice, and mobile convergence-extending the triple play. Texas Instruments White Paper (2004)Google Scholar
  32. 32.
    Jakes, W.: Microwave Mobile Communications. IEEE Press, New York (1993)Google Scholar
  33. 33.
    Choi, J., Bouchard, M., Yeap, T.: Decision feedback recurrent neural equalization with fast convergence rate. IEEE Trans. Neural Networks 16(3), 699–708 (2005)CrossRefGoogle Scholar
  34. 34.
    Potter, C., Venayagamoorthy, G.K., Kosbar, K.: MIMO beam-forming with neural network channel prediction trained by a novel PSO-EA-DEPSO algorithm. In: 2008 IEEE World Congress Computational Intelligence/2008 IEEE Int. Joint Conf. Neural Networks, Hong Kong, June 1-6, pp. 3338–3344 (2008)Google Scholar
  35. 35.
    Jacson, L.: Digital Filters and Signal Processing. Kluwer, Norwell (1989)Google Scholar
  36. 36.
    Paulraj, A., Nabar, R., Gore, D.: Introduction to Space-Time Wireless Communications. Cambridge University, Cambridge (2003)Google Scholar
  37. 37.
    Bain, L., Engelhardt, M.: Introduction to Probability and Mathematical Statistics. Brooks/Cole, Pacific Grove (1992)zbMATHGoogle Scholar
  38. 38.
    Lee, W.: Mobile communication engineering. McGraw Hill, New York (1982)Google Scholar
  39. 39.
    Fu, J., Taniguchi, T., Karasawa, Y.: The largest eigenvalue characteristics for mimo channel with spatial correlation. J. Global Optimization 6(2), 109–133 (1995)CrossRefGoogle Scholar
  40. 40.
    Goldsmith, A.: Wireless Communications. Cambridge University Press, New York (2005)Google Scholar
  41. 41.
    Karagiannidis, G., Lioumpas, A.: An improved approximation for the gaussian q function. IEEE Communications Letters 11(8), 644–646 (2007)CrossRefGoogle Scholar
  42. 42.
    Gradshteyn, S., Ryzhik, I., Jeffrey, A.: Table of Integrals, Series, and Products, 5th edn. Academic, San Diego (2007)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2010

Authors and Affiliations

  • Chris Potter
    • 1
  1. 1.Dynetics Inc 

Personalised recommendations