Using recurrent neural network for adaptive predistortion linearization of RF amplifiers

A novel adaptive predistorter for linearizing a power amplifier in a mobile transmitter is studied. Unlike most other predistorters reported in the literatures, this predistorter is constructed as a complex-valued recurrent neural network (RNN). The weights of the RNN were adjusted by using complex real time recurrent learning (RTRL) algorithm. Thus the AM/AM and AM/PM responses of the proposed predistorter are simultaneously implemented. The proposed scheme is shown to attain superior performance in comparison with other most well-known predistortion structures. The performance of the proposed predistorter is demonstrated through computer simulations.