A Comparison of Adaline and MLP Neural Network based Predictors in SIR Estimation in Mobile DS/CDMA Systems

In this paper we compare the response of linear and nonlinear neural network-based prediction schemes in prediction of received Signal-to-Interference Power Ratio (SIR) in Direct Sequence Code Division Multiple Access (DS/CDMA) systems. The nonlinear predictor is Multilayer Perceptron MLP and the linear predictor is an Adaptive Linear (Adaline) predictor. We solve the problem of complexity by using the Minimum Mean Squared Error (MMSE) principle to select the optimal predictors. The optimized Adaline predictor is compared to optimized MLP by employing noisy Rayleigh fading signals with 1.8 GHZ carrier frequency in an urban environment. The results show that the Adaline predictor can estimates SIR with the same error as MLP when the user has the velocity of 5 km/h and 60 km/h but by increasing the velocity up-to 120 km/h the mean squared error of MLP is two times more than Adaline predictor. This makes the Adaline predictor (with lower complexity) more suitable than MLP for closed-loop power control where efficient and accurate identification of the time-varying inverse dynamics of the multi path fading channel is required.

Authors:

• Nahid Ardalani
• Ahmadreza Khoogar
• H. Roohi

Keywords:

• Power control
• neural networks
• DS/CDMA mobilecommunication systems.

References:

[1] R. Prasad, CDMA for Wireless Personal Communications, Artech
House, 1996.
[2] S. Soliman, C. Wheatley, and R. Padovani, "CDMA reverse link open
loop power control," in Proceedings IEEE Global
Telecommunications Conference, vol. 1, December 1992.
[3] S. Ariyavisitakul and L. F. Chang, "signal and interference statistics of
a CDMA system with feed back power control," IEEE Transactions on
Communications, vol. 41, no. 11, November 1993.
[4] A. Kurniawan, Predictive Power Control in CDMA Systems, p.h.d
Dissertation, The University of South Australia, Feb. 2003.
[5] F. C. M. Lau and W. M. Tarn, "Novel SIR-Estimation-Based Power
Control in a CDMA Mobile Radio System Under Multipath
Environment," IEEE Transactions on Vehicular Technology, vol. 50,
No. 1, January 2001.
[6] F. C. M. Lau and W. M. Tarn, "Achievable-SIR-Based Predictive
Closed-Loop Power Control in a CDMA Mobile System," IEEE
Transactions on Vehicular Technology,vol. 51, No. 4, July 2002.
[7] D. P. Mandic and J. A. Champers, Recurrent Neural Networks for
Prediction Learning Algorithms Architecture and Stability, 2001.
[8] B. Varone, J. M. A. Tanskanen, and S. J. Ovaska, "Response analysis
of feed-forward neural network predictors," in Proc. 1997
International Conference on Acoustics, Speech, and Siganl Processing,
pp. 3309-3312, April 1997.
[9] T. Miyajima, T. Hasegawe, and M. Haneishi, "On the multiuser
detection using a neural network in code-division multiple access
communications," IEICE Transactions on Communication, vol. 76,
Aug. 1993.
[10] X. M. Gao, X. Z. Gao, J. M. A. Tanskanen, and S. J. Ovaska, "Power
prediction in mobile communication systems using an optimal neuralnetwork
structure," IEEE Trans. on Neural Networks, vol. 8, no. 6,
November 1997.
[11] X. Z. Gao, X. M. Gao, and S. J. Ovaska, "A modified neural network
model with application to dynamical systems identification," In
proceeding of the 1996 IEEE International Conference on Systems,
October 1996.
[12] P. Heinonen and Y. Neuvo, "FIR-median hybrid filters with predictive
FIR substructures," IEEE Trans. Acoustic Speech Signal Processing,
vol. 36, pp. 829-899, June 1988.
[13] W. C. Jake, Microwave Mobile Communications, Newyork,
Johnwilley, 1994.
[14] W. R. Braun, and U. Dersch, "A physical mobile radio channel
model," IEEE Trans. on Vehicular Technology, Vol.VT-40, no. 2,
May 1991.
[15] A. J. Viterbi, Principles Of Spread Spectrum Communication,
Reading: Addition-wesley , 1995.
[16] R. L. Peterson, R. E. Ziemer, and D. E. Borth, Introduction to Spread
Spectrum Communications, Singapore, Prentice Hall international,
1995.
[17] J. G. Proakis, Digital Communications, Newyork: McGraw-Hill, 1995.
[18] M. Cottrell, B. Girard, Y. Girard, M. Mangeas, and C. Muller, "Neural
modeling for time series: A statistical stepwise method for weight
elimination," IEEE Trans. Neural Networks, vol. 6, pp. 1355-1364,
Nov. 1995.
[19] W. Finnoff, F. Hergert, and H. G. Zimmermann, "Improve
generalization performance by nonconvergent model selection
methods," Neural Networks, vol. 6, pp. 771-783, June 1991.
[20] X. M. Gao, S .J. Ovaska, and I. O. Hartimo, "Restoration of noisy
speech using an optimal neural network structure," IEEE International
Conference on neural networks, vol. 8, no. 6, November 1997.
[21] X. M. Gao, S. J. Ovaska, M. Lehtokangas, and J. Saarinen, "Modeling
of speech signals using an optimal neural-network structure based on
the PMDL principle," in IEEE Trans. Speech Audio Processing, vol.
5, 1998.
[22] J. Tanskanen, Multiuser CDMA Power Control Simulator-Efeects of
Simple Prediction, Licentiate of Technology Thesis, Helsinki
University of Technology, Espoo, Finland, Jan. 1999.
[23] A. Cichocki, and R. Unbehauen, Neural Network for Optimization and
Signal Processing, 1993.
[24] V. Ruiz, D. Angulo, and C. Torras, "On-line learning with minimal
degradation in feed forward networks," IEEE Trans. Neural Networks,
vol. 6, pp. 657-668, May 1995.
[25] E. Aarts and P. Van Laarhoven, Simulated Annealing, Theory and
Practice. New York Wiley, 1987.
[26] N. Ardalani, H. Roohi, A. Khoogar, "SIR prediction in mobile CDMA
systems by an optimal neural-network-based predictor," in Proceeding
of the First International Conference on Modeling, Simulation and
Applied Optimization, Sharjah, U.A.E. February 2005.