Digital Predistortion of RF Power Amplifiers With Phase-Gated Recurrent Neural Networks

Abstract

In this article, we present a novel recurrent neural network (RNN)-based behavioral model to linearize radio frequency (RF) power amplifiers (PAs) under wideband excitations. Based on the lightweight Just Another NETwork (JANET) unit, we propose a new neural network structure that is especially suitable for modeling the complex behavior of the RF PAs. A novel signal preprocessing technique is developed to model the complex interaction between amplitude information and phase information in the digital predistortion (DPD) model. By integrating the preprocessing stage into the RNN model, the complete phase-gated JANET (PG-JANET) model can provide enhanced linearization performance with lower complexity compared to the existing models.

Digital Predistortion of RF Power Amplifiers With Decomposed Vector Rotation-Based Recurrent Neural Networks

“…Moreover, ⊗ and σ represent the element-wise multiplication and the sigmoid activation function, respectively. From the results given in [22], we can see that the output function h n of JANET can be attributed to the PA behavior described via a recurrent feedback structure that can cover long-term memory effects. The JANET network is a single gate simplified model of long short-term memory (LSTM) network, which provides high-accuracy performance with low complexity.…”

“…On the one hand, the rightly fit model can accurately catch the physical dynamics of the PA. On the other hand, removing redundant terms is beneficial in reducing the complexity for practical implementation. In our previous work in [22], we carefully examined the relationship between the physical behavior of the PA and the neural network structures and proposed a modified version of recurrent neural networks, called PG-JANET, to model the PA and conduct the DPD.…”

“…Some recent works have proposed recurrent DPD models [16], [17], [18], [19], but none of the revised networks concentrate on the search for the most suitable network structure. In [22], a useful link between the lightweight Just Another NETwork (JANET) [23] and the physical behavior of the PA is established. After adopting a new model structure, the phase-gated recurrent neural network-based DPD model, phase-gated JANET (PG-JANET), proposed in [22], achieved remarkable improvement in modeling accuracy and linearization performance.…”

“…In [22], a useful link between the lightweight Just Another NETwork (JANET) [23] and the physical behavior of the PA is established. After adopting a new model structure, the phase-gated recurrent neural network-based DPD model, phase-gated JANET (PG-JANET), proposed in [22], achieved remarkable improvement in modeling accuracy and linearization performance. However, a large number of coefficients are still required when linearizing wideband PAs.…”

“…In this article, we significantly improve our prior work in [22] and propose a novel decomposed vector rotation (DVR)-based recurrent network to better model the complex nonlinearity and longer memory effects of the PA and, therefore, to ensure a more practical design. Based on the methodical analysis of recurrent operation and DVR model structure [24], we find that it is possible to represent memory terms within the model with recurrent states.…”