Channel Estimation in Massive MIMO Systems Using a Modified Bayes-GMM Method

  • Pan SuEmail author
  • Yang Wang


In this paper, we study the uplink channel estimation based on machine learning algorithm in massive MIMO systems. Based on the sparsity of channel gains in the beam domain, we use Gaussian mixture model (GMM) to model the channel. The expectation maximization (EM) algorithm is adopted to obtain the parameters of GMM. Bayesian algorithm is used to estimate the channel gains. The approximate message passing (AMP) algorithm is used to solve the multiple integrals in Bayesian estimation algorithm to reduce the computational load. When determining the initial values of AMP and EM algorithms, the hierarchical clustering algorithm is adopted to improve the mean square error (MSE) and convergence performance of the algorithm. Simulation results show that the performance of the proposed algorithm is better than that of the traditional least square (LS) algorithm and the existing Bayes-GMM algorithm.


Channel estimation GMM Bayesian estimation Hierarchical clustering 



This work was supported by the National Natural Science Foundation of China (No. 61271235) and the open research fund of Key Lab of Broadband Wireless Communication and Sensor Network Technology (Nanjing University of Posts and Telecommunications), Ministry of Education.


  1. 1.
    Qiao, Y., Yu, S., Su, P., et al. (2005). Research on an iterative algorithm of LS channel estimation in MIMO OFDM systems. IEEE Transactions on Broadcasting, 51(1), 149–153.CrossRefGoogle Scholar
  2. 2.
    Zamirijafarian, H., & Pasupathy, S. (2007). MIMO-OFDM channel estimation using improved LS algorithm. In Vehicular technology conference, 2006. Vtc-2006 Fall. 2006 IEEE (pp. 1–5). IEEE.Google Scholar
  3. 3.
    Srivastava, V., Ho, C. K., Fung, P. H. W., et al. (2004). Robust MMSE channel estimation in OFDM systems with practical timing synchronization. In Wireless communications and networking conference, 2004. WCNC. (Vol. 2, pp. 711–716). IEEE.Google Scholar
  4. 4.
    Noh, M., Lee, Y., & Park, H. (2006). Low complexity LMMSE channel estimation for OFDM. IEE Proceedings-Communications, 153(5), 645–650.CrossRefGoogle Scholar
  5. 5.
    Kang, Y., Kim, K., & Park, H. (2007). Efficient DFT-based channel estimation for OFDM systems on multipath channels. IET Communications, 1(2), 197–202.CrossRefGoogle Scholar
  6. 6.
    Lebrun, G., Spiteri, S., & Faulkner, M. (2004). Channel estimation for an SVD-MIMO system. IEEE International Conference on Commun, 5, 3025–3029.Google Scholar
  7. 7.
    Robert, C. (2014). Machine learning, a probabilistic perspective. Chance, 27(2), 62–63.CrossRefGoogle Scholar
  8. 8.
    Wen, C.-K., Jin, S., Wong, K.-K., et al. (2015). Channel estimation for massive MIMO using Gaussian-mixture bayesian learning. IEEE Transactions on Wireless Communications, 14(3), 1356–1368.CrossRefGoogle Scholar
  9. 9.
    Hoydis, J., Hoek, C., Wild, T., et al. (2012). Channel measurements for large antenna arrays. In International symposium on wireless communication systems (pp. 811–815). IEEE.Google Scholar
  10. 10.
    Bajwa, W. U., Haupt, J., Sayeed, A. M., et al. (2010). Compressed channel sensing: A new approach to estimating sparse multipath channels. Proceedings of the IEEE, 98(6), 1058–1076.CrossRefGoogle Scholar
  11. 11.
    Shiu, D. S., Faschini, G. J., Gans, M. J., et al. (2002) Fading correlation and its effect on the capacity of multi-element antenna systems. In IEEE 1998 international conference on universal personal communications (pp. 502–513). IEEE.Google Scholar
  12. 12.
    Sun, C., Gao, X., Jin, S., et al. (2015). Beam division multiple access transmission for massive MIMO communications. IEEE Transactions on Communications, 63(6), 2170–2184.CrossRefGoogle Scholar
  13. 13.
    Adhikary, A., Nam, J., Ahn, J.-Y., et al. (2013). Joint spatial division and multiplexing: The large-scale array regime. IEEE Transactions on Information Theory, 59(10), 6441–6463.MathSciNetCrossRefzbMATHGoogle Scholar
  14. 14.
    Payami, S., & Tufvesson, F. (2012). Channel measurements and analysis for very large array systems at 2.6 GHz. In European conference on antennas and propagation (pp. 433–437). IEEE.Google Scholar
  15. 15.
    Pedersen, K. I., Mogensen, P. E., & Fleury, B. H. (1997). Power azimuth spectrum in outdoor environments. IEE Electronics Letters, 33(18), 1583–1584.CrossRefGoogle Scholar
  16. 16.
    Correia, L. M. (2001). Wireless flexible personalized communications. Computer Communications, 26(18), 2106.Google Scholar
  17. 17.
    Alspach, D. L., & Sorenson, H. W. (2003). Nonlinear Bayesian estimation using Gaussian sum approximations. IEEE Transactions on Automatic Control, 17(4), 439–448.CrossRefzbMATHGoogle Scholar
  18. 18.
    Zellner, A. (1986). Bayesian estimation and prediction using asymmetric loss functions. Publications of the American Statistical Association, 81(394), 446–451.MathSciNetCrossRefzbMATHGoogle Scholar
  19. 19.
    Poor, H. V. (1994). An introduction to signal detection and estimation. New York, NY: Springer.CrossRefzbMATHGoogle Scholar
  20. 20.
    Krzakala, F., Mézard, M., Sausset, F., et al. (2012). Probabilistic reconstruction in compressed sensing: Algorithms, phase diagrams, threshold achieving matrices. Journal of Statistical Mechanics: Theory and Experiment, 2012(8), P08009.CrossRefGoogle Scholar
  21. 21.
    Hirsch, J. E. (1983). Discrete hubbard-stratonovich transformation for fermion lattice models. Physical Review B, 28(7), 4059–4061.CrossRefGoogle Scholar
  22. 22.
    Bromiley, P. A. (2003). Products and convolutions of Gaussian probability density functions density functions. Tina Memo Internal Report, 2003(3), 1–13.Google Scholar
  23. 23.
    Vila, J. P., & Schniter, P. (2012). Expectation-maximization Gaussian-mixture approximate message passing. IEEE Transactions on Signal Processing, 61(19), 4658–4672.MathSciNetCrossRefzbMATHGoogle Scholar
  24. 24.
    Johnson, S. C. (1967). Hierarchical clustering schemes. Psychometrika, 32(3), 241–254.CrossRefzbMATHGoogle Scholar

Copyright information

© Springer Science+Business Media, LLC, part of Springer Nature 2019

Authors and Affiliations

  1. 1.College of Telecommunications and Information EngineeringNanjing University of Posts and TelecommunicationsNanjingChina
  2. 2.Key Lab of Broadband Wireless Communication and Sensor Network TechnologyNanjing University of Posts and Telecommunications, Ministry of EducationNanjingChina

Personalised recommendations