Reinforcement Learning-Based Power Control in Mobile Communications Systems

Abstract In this paper, a Muller’s method–based fast reinforcement learning algorithm is proposed. This new algorithm converges much faster than the conventional approach, and is therefore more suitable for on–line applications. We apply the presented reinforcement learning algorithm into the power control of cellular phones systems. Both the mobile channel tracking error and control output can be minimized in our power regulation scheme. Simulation experiments demonstrate that harmful deep fading is significantly compensated, while the overshoots in response are also small.

[1]  W. C. Jakes,et al.  Microwave Mobile Communications , 1974 .

[2]  Seppo J. Ovaska,et al.  Power prediction using an optimal neuro-fuzzy predictor , 1997, IEEE Instrumentation and Measurement Technology Conference Sensing, Processing, Networking. IMTC Proceedings.

[3]  Athanasios V. Vasilakos,et al.  Temporal difference method-based multi-step ahead prediction of long term deep fading in mobile networks , 2002, Comput. Commun..

[4]  Kendall E. Atkinson.  An introduction to numerical analysis , 1978 .

[5]  Kurt Hornik,et al.  Multilayer feedforward networks are universal approximators , 1989, Neural Networks.

[6]  Seppo J. Ovaska,et al.  A modified Elman neural network model with application to dynamical systems identification , 1996, 1996 IEEE International Conference on Systems, Man and Cybernetics. Information Intelligence and Systems (Cat. No.96CH35929).

[7]  John N. Tsitsiklis,et al.  Neuro-Dynamic Programming , 1996, Encyclopedia of Machine Learning.

[8]  Philip E. Gill,et al.  Practical optimization , 1981 .

[9]  Richard S. Sutton,et al.  Neuronlike adaptive elements that can solve difficult learning control problems , 1983, IEEE Transactions on Systems, Man, and Cybernetics.

[10]  Seppo J. Ovaska,et al.  Power control for mobile DS/CDMA systems using a modified Elman neural network controller , 1997, 1997 IEEE 47th Vehicular Technology Conference. Technology in Motion.

[11]  Albert Y. Zomaya.  Reinforcement learning for the adaptive control of nonlinear systems , 1994 .

[12]  Chin-Teng Lin,et al.  A neural fuzzy system with linguistic teaching signals , 1995, IEEE Trans. Fuzzy Syst..

[13]  Andrew J. Viterbi,et al.  On the capacity of a cellular CDMA system , 1991 .

[14]  Xiao Zhi Gao,et al.  Fuzzy Power Command Enhancement in Mobile Communications Systems , 2001, Int. J. Comput. Intell. Appl..

[15]  Xiao Zhi Gao,et al.  Comparison of conventional and soft computing-based power control methods in mobile communications systems , 2001, Soft Comput..