Title :
Data predistortion with adaptive fuzzy systems
Author :
Li, Ying ; Yang, Po-Hsun
Author_Institution :
Electr. Eng. Dept., Yuan-Ze Univ., Taoyuan, Taiwan
Abstract :
Presents two data predistortion methods for communication transmitters that employ adaptive fuzzy systems. The first is based on indirect learning and does not require a model of the high power amplifier. The second requires an estimated model of the pulse shaping filter and the high power amplifier before training. Simulations with 16 QAM signals show that the performance of fuzzy predistorters are roughly the same as the performance of a third order polynomial predistorter with odd-ordered terms only. Fuzzy and polynomial predistorters in the second method both contain nonlinear parameters, which are sensitive to initial conditions. The fuzzy predistorter has the unique advantage in that the initial values of all adjustable parameters can be set easily based on their linguistic meanings
Keywords :
Volterra series; adaptive filters; filtering theory; fuzzy neural nets; fuzzy set theory; fuzzy systems; nonlinear filters; power amplifiers; pulse shaping circuits; quadrature amplitude modulation; radio transmitters; QAM signals; adaptive fuzzy systems; communication transmitter; data predistortion methods; fuzzy predistorters; high power amplifier; indirect learning; odd-ordered terms; pulse shaping filter; third order polynomial predistorter; Adaptive systems; Filters; Fuzzy systems; High power amplifiers; Polynomials; Power system modeling; Predistortion; Pulse shaping methods; Quadrature amplitude modulation; Transmitters;
Conference_Titel :
Systems, Man, and Cybernetics, 1999. IEEE SMC '99 Conference Proceedings. 1999 IEEE International Conference on
Conference_Location :
Tokyo
Print_ISBN :
0-7803-5731-0
DOI :
10.1109/ICSMC.1999.816512
