Title :
Recurrent neural networks usefulness in digital pre-distortion of power amplifiers
Author :
Ciminski, Andrzej S.
Author_Institution :
Vallingbyvagen, Vallingby, Sweden
Abstract :
Digital pre-distortion techniques are widely utilized in linearization of RF power amplifiers. In this paper recurrent neural networks are used to model an inverse function of the power amplifier. This function predistorts an input signal in digital domain in order to increase the linearity of the modeled power amplifier. The simulation results are presented.
Keywords :
distortion; microwave power amplifiers; recurrent neural nets; RF power amplifier linearization; digital pre-distortion; inverse function; power amplifiers; recurrent neural networks; Costs; Intelligent networks; Inverse problems; Linearity; Linearization techniques; Nonlinear distortion; Power amplifiers; Power generation; Radiofrequency amplifiers; Recurrent neural networks;
Conference_Titel :
Microwaves, Radar and Wireless Communications, 2004. MIKON-2004. 15th International Conference on
Print_ISBN :
83-906662-7-8
DOI :
10.1109/MIKON.2004.1356909
