Predistortion Model Research Articles

A hybrid memory polynomial digital predistortion model for RF transmitters

The power amplifier (PA), a key component of the transmitter system, operates near the saturation region, resulting in nonlinear distortion of the output signal, which affects the quality of the transmitter system. For this, a series of linearization techniques are used to compensate for distortion, one of the most effective and widely applied is the digital predistortion (DPD) technique. The traditional DPD models can be categorized into a single model or multiple models cascade or parallel. In this letter, a hybrid memory polynomial (HMP) model is proposed to further enhance the accuracy of the model, which is composed of multiple memory polynomial (MP) models by cascading and parallelizing. The experimental results show that the HMP model has better accuracy than the traditional MP model at the same complexity.

An Integrated Scheme of FIR and Augmented Real-Valued Time-Delay Neural Network of Harmonic Cancellation Digital Predistortion Model for High-Frequency Power Amplifier

An Integrated Scheme of FIR and Augmented Real-Valued Time-Delay Neural Network of Harmonic Cancellation Digital Predistortion Model for High-Frequency Power Amplifier

Decomposed Vector Combination-Based Low-Complexity Behavioral Model for Digital Predistortion of RF Transmitters

Decomposed Vector Combination-Based Low-Complexity Behavioral Model for Digital Predistortion of RF Transmitters

Adaptive Inference Pathway-Gated Neural Network Model for Digital Predistortion With Varying Transmission Configurations

Adaptive Inference Pathway-Gated Neural Network Model for Digital Predistortion With Varying Transmission Configurations

Dual Feature Indexed Quadratic Polynomial-Based Piecewise Behavioral Model for Digital Predistortion of RF Power Amplifiers

Dual Feature Indexed Quadratic Polynomial-Based Piecewise Behavioral Model for Digital Predistortion of RF Power Amplifiers

Real-Time Optimization of Dynamic Predistortion Model for 5G Massive MIMO Broadband RF Power Amplifier

Real-Time Optimization of Dynamic Predistortion Model for 5G Massive MIMO Broadband RF Power Amplifier

Vector-switched digital predistortion for concurrent dual-band transmitters with hybrid time-division multiplexing scheme

In a concurrent dual-band digital predistortion (DPD) system, due to the large number of two-dimensional (2D) polynomial-based model coefficients and the existence of cross-modulation terms, the hardware realization usually requires a lot of resources. To alleviate this problem, this paper proposes a hardware-efficient field programmable gate array (FPGA)-based piecewise vector-switched (PVS) DPD method. With the PVS method, a 2D memory polynomial (MP) model with fewer coefficients can be used as a sub predistorter model for each region. Furthermore, a new hybrid time-division multiplexing (HTDM) scheme is proposed for the 2D-MP predistorter architecture, which enables sharing of cross-modulated lookup tables (LUTs) and complex multipliers in a hybrid way. Experimental results show that the proposed method improves the adjacent channel power ratio (ACPR) and normalized mean square error (NMSE) by 18.74 dB and 13.23 dB, respectively, and saves about 30% and 80% of RAM and DSP resources, respectively.

Gated Dynamic Neural Network Model for Digital Predistortion of RF Power Amplifiers With Varying Transmission Configurations

The future intelligent transmitter will dynamically adjust the transmission configuration on demand, which will bring new challenges to digital predistortion (DPD). In this article, we present a gated dynamic neural network (GDNN) DPD model to linearize the power amplifier (PA) with varying transmission configurations. The proposed GDNN model is composed of a gating network and a backbone network that can be any NN-based DPD model designed for a fixed configuration. The core idea of the GDNN model is that the backbone model can be dynamically adjusted using the configuration-dependent weights generated by the gating network to achieve transmission configuration-adaptive DPD. To further reduce the running complexity of the GDNN DPD, a sparse GDNN (SGDNN) DPD model is also proposed, which selectively activates the neurons of the backbone network according to the transmission configuration. Experiments are performed with a Doherty PA to validate the proposed method, where the varying transmission configuration includes power level, signal bandwidth (BW), and peak-to-average power ratio. The test results demonstrate that the proposed method can effectively linearize the PA with dynamic transmission configuration and has excellent configuration generalization capability. Moreover, the sparse gating technique can reduce the running complexity of the GDNN DPD by more than 50 <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$\%$</tex-math> </inline-formula> with only a slight performance loss.

Multi-Output Recurrent Neural Network Behavioral Model for Digital Predistortion of RF Power Amplifiers

In this letter, we propose a method for behavioral modeling and digital predistortion (DPD) of RF power amplifiers (PAs) based on multi-output recurrent neural networks (RNNs). RNN has high modeling accuracy, but it also has high running complexity due to the recurrent mechanism. For this reason, we propose a multi-output model architecture, which means that the DPD model produces multiple adjacent outputs simultaneously for a single input sample group. This approach greatly reduces the running complexity of DPD based on RNNs with essentially no deterioration in performance. The proposed multi-output mechanism is applied to both long short-term memory (LSTM) and gate recurrent unit (GRU), and excellent linearization performances are maintained.

Attention mechanism based bidirectional LSTM model for broadband power amplifier linearization

AbstractIn this letter, a novel digital predistortion (DPD) model for broadband power amplifier (PA) linearization is proposed, namely Attention Mechanism based Bidirectional Long Short‐term Memory Network (AM‐BiLSTM) model. In order to verify the linearization performance of the AM‐BiLSTM model in digital predistortion process, a 100 MHz bandwidth 5G new radio (5G NR) signal is employed to test a sub‐6G PA operating at 2.6‐GHz. The experimental results show that the adjacent channel power ratio (ACPR) of the PA with AM‐BiLSTM model can be improved by 24 dB which is 6 dB and 3 dB better than the generalized memory polynomial (GMP) model and the Chebyshev polynomials LSTM (CP‐LSTM) model in ref [1], repspectively. Therefore, the proposed AM‐BiLSTM model is very effective for the DPD linearization of broadband PAs.

An Integrated Scheme of Cross-FIR-LUT Harmonic Cancellation Digital Predistortion Model for Short-Wave Power Amplifier

Intermodulation distortion (IMD) and higher harmonics caused by the nonlinearity of power amplifier (PA) are the main problems of multioctave PA used in high-frequency (HF) transmitter. In this letter, the integrated structured digital predistortion (DPD) method is proposed based on the characteristics of short-wave signal systems. Based on the integrated cross-memory polynomial DPD model, the FIR structure with low-pass filtering characteristics is further employed to achieve the goal of improving baseband IMD while suppressing higher order harmonics of multioctave HF PAs. Experimental results on a real HF PA illustrate that the proposed CROSS-FIR-lookup table (LUT) improves the baseband IMD about <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$\text{10}$</tex-math> </inline-formula> dB, while the second and third harmonics are below <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$-$</tex-math> </inline-formula> 55 dB, compared with the conventional MP and GMP schemes without increasing the algorithm complexity.

A Novel Digital Predistortion Identification Algorithm Based on Variable Forgetting Factor Recursive Least Square Method

The transmitting signal of wireless communication system is impaired by the nonlinearity of RF power amplifier (PA) which leads to signal distortion and spectrum spillover, by which the signal transmission quality is affected. Digital predistortion (DPD) is an efficient and economical way to correct the nonlinear effects of power amplifiers. The recursive least square (RLS) recognition algorithm is commonly used to extract the correction coefficients of the DPD model, and the accuracy of the extraction directly affects the system performance. In this paper, a new variable forgetting factor identification algorithm (new variable forgetting factor recursive least square, NVFFRLS) is proposed for recursive least square (RLS) identification algorithm. The 64-QAM signal is combined with a memory polynomial (MP) predistortion model for predistortion system simulation. The experimental results show that, compared with the RLS identification algorithm and two kinds of variable forgetting factor RLS identification algorithms, the algorithm has smaller estimation error, faster convergence, and better tracking capability, stability, and adaptability; the predistortion system based on NVFFRLS identification algorithm can compensate the nonlinear memory effects of power amplifier more effectively.

Low Complexity Adaptive Model for Digital Predistortion of RF Power Amplifiers in Time-Varying Configurations

A novel behavioral modeling approach called adaptive model tree (AMT) is proposed for digital predistortion (DPD) of RF power amplifiers (PAs) in fixed and time-varying configurations. The AMT model is piecewise based on the decision tree and the reduced-complexity full basis-propagating selection (RC-FBPS) model. A novel two-step joint iterative algorithm is proposed to achieve a good match between the decision tree and the submodels obtained from the RC-FBPS model. The AMT model inherits and enhances the respective advantages of the decision tree and RC-FBPS model to have a powerful adaptive capability potentially. The experimental tests on a Doherty PA confirm that the AMT model can achieve a better trade-off between linearization performance and complexity than the state-of-the-art model in the fixed configuration. Furthermore, to characterize and compensate for the complex dynamic nonlinear distortions of PAs in time-varying configurations, the piecewise modeling technique in time-varying configurations is proposed and applied to the AMT model in this article. The experimental results confirm that the AMT model achieves excellent linearization performance with very low complexity in time-varying configurations and good generalization performance for new configuration combinations that are not used for training.

Artificial Intelligence-Based Power-Temperature Inclusive Digital Predistortion

This article investigates the effects of the average power variation and the ambient temperature on the behavioral modeling and predistortion of high-power amplifiers concurrently. The measurement results showed that in addition to the average power variation, the behavior of a high-power PA is a function of ambient temperature as well. This article proposes a novel smart digital predistortion (DPD) model that considers both average power variation and temperature (PTI-DPD). The PTI-DPD is implemented using artificial intelligence-based model and it benefits from sets of data formats containing the signal, its delayed versions, average power variation, and ambient temperature. The developed architecture provides an uninterrupted linearization across the ambient temperature and average power variation span without need for a continues feedback path or multiple models. A series of measurements have been conducted to study the PTI-DPD performance across the temperature and average power range. According to the results, the PTI-DPD achieves an average of −48.5 dBc adjacent channel power ratio across the average power and temperature span.

A Uniform Neural Network Digital Predistortion Model of RF Power Amplifiers for Scalable Applications

In this article, a uniform neural network (NN) digital predistortion (DPD) model of radio frequency (RF) power amplifiers (PAs) is proposed for dynamic applications, which is suitable for RF PAs under various operating conditions without updating the coefficients. With the development of communication systems, it is difficult for the DPD to track the nonlinearity of the PA as the operating condition varies frequently. As one of the most promising achievements in recent years, the NN has shown excellent generalization ability, which is applicable to the DPD for scalable applications. In this situation, a uniform neural network model (UNNM), whose structure is a two-stage network, is proposed for scalable output power, scalable bandwidth, or simultaneous scalable power and bandwidth. The experiments are carried out on two sub-6 GHz broadband GaN Doherty PAs (DPAs). The experimental results show that the proposed model can achieve comparable performance without coefficient update in the scalable output power range of about 5 dB and the bandwidth range of 100 MHz, which outperforms the conventional fixed model with better than 3 dB power range and 40 MHz bandwidth range.

A Low Running Complexity Model for Digital Predistortion of RF Power Amplifiers

In this letter, two basis function multiplexing-based behavioral modeling methods for digital predistortion (DPD) of RF power amplifiers (PAs) are proposed to reduce the running complexity of DPD. The proposed full basis-propagating selection (FBPS) model and reduced-complexity FBPS (RC-FBPS) model give two reasonable ways to multiplex even-order basis functions, extending the basis-propagating selection (BAPS) model which only uses basis function delay and odd-order basis functions. The experimental results confirm that both the proposed FBPS and RC-FBPS models can achieve a good tradeoff between running complexity and performance.

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

In this article, we present a novel decomposed vector rotation (DVR)-based recurrent neural network behavioral model for digital predistortion (DPD) of radio frequency (RF) power amplifiers (PAs) in wideband scenarios. By representing memory terms of DVR with recurrent states and redesigning the piecewise modeling, we propose a novel recurrent DVR scheme. To ensure stable operation and enhanced modeling accuracy, we integrate the recurrent DVR into the gated learning mechanism of the modified Just Another NETwork (JANET). Experimental results confirm that the proposed DVR-JANET model provides much improved linearization performance with significantly reduced model complexity compared with the recent existing models.

A Tangent Approximation Coefficient Extraction Method for Instantaneous Sample Indexed Magnitude-Selective Affine Behavioral Model

The coefficients of digital predistortion (DPD) models are often extracted by the least square (LS) method, which has high computational complexity because of the operations of the large matrix. In this letter, a low complexity coefficient extraction method for instantaneous sample indexed magnitude-selective affine (I-MSA) model is proposed. The proposed method uses the tangent of the midpoint of the piecewise function to fit the curve. Therefore, the LS coefficient extraction only needs a small amount of data near the midpoint, rather than using all the data in the segmented region. Simulation and experimental results have confirmed that compared with the original LS method, the proposed method has similar modeling accuracy and linearization performance, but the computational complexity of coefficient extraction is greatly reduced.

A pruning method of feedforward neural network based on contribution of input components for digital predistortion of power amplifier

AbstractIn this paper, a pruning method based on contribution of input components is proposed to optimize the structure of Feedforward neural network (FNN) model for digital predistortion of power amplifier. The optimized hyperparameters are the specific input components. The pruning algorithm is divided into two stages. The stage I is used to rough rank the importance of input components and the stage II is used to modify the results of stage I. Then, we can get an importance ranking of input components. By deleting unimportant input components, a pruned FNN model with fewer input components can be obtained. Test results show that the proposed algorithm can greatly simplify the FNN model on the premise of ensuring the predistortion performance.

A Sparse-Bayesian Approach for the Design of Robust Digital Predistorters Under Power-Varying Operation

In this article, a sparse-Bayesian treatment is proposed to solve the crucial questions posed by power amplifier (PA) and digital predistorter (DPD) modeling. To learn a model, the advanced Bayesian framework includes a group of specific processes that maximize the likelihood of the measured data: regressor pursuit and identification, coefficient estimation, stopping criterion, and regressor deselection. The relevance vector machine (RVM) method is reformulated theoretically to be implemented in complex-valued linear regression. In essence, given an initial set of candidate regressors, the result of this sparse-Bayesian learning approach is the most likely model. Experimental results are provided for the linearization of class AB and class J PAs driven by a 30-MHz fifth-generation new radio signal for a fixed average power, where the evolution of the figures of merit versus the number of active coefficients is examined for the proposed sparse-Bayesian pursuit (SBP) algorithm in comparison to other greedy algorithms. The SBP presents a good performance in terms of linearization capabilities and computational cost. Furthermore, the proposed Bayesian framework enabled the design of a DPD model structure, deselect regressors, and readjust coefficients in a direct learning architecture, demonstrating the robustness to changes in the power level over a 10-dB range.