A Basis Function Generation Based Digital Predistortion Concurrent Neural Network Model of RF Power Amplifier

Abstract: This paper proposes a concurrent neural network model to mitigate non-linear distortion in power amplifiers using a basis function generation approach. The model is designed using polynomial expansion and comprises a feedforward neural network (FNN) and a convolutional neural network (CNN). The proposed model takes the basic elements that form the bases as input,  defined by the generalized memory polynomial (GMP) and dynamic deviation reduction (DDR) models. The FNN generates the basis function and its output represents the basis values, while the CNN  generates weights for the corresponding bases. Through concurrent training of FNN and CNN, the hidden layer coefficients are updated, and the complex multiplication of their outputs yields the trained in-phase and quadrature (IQ) signal. The proposed model was trained and tested using 300 MHz and 400 MHz broadband data in an orthogonal frequency division multiplexing (OFDM) communication system. The results show that the model achieves an adjacent channel power ratio (ACPR) of less than –48 dB within a 100 MHz integral bandwidth for both the training and test datasets.

Keywords: basis function generation; digital predistortion; generalized memory polynomial; dynamic deviation reduction, neural network