2026· EPJ Web of Conferences· Vol 380, pp. 01008· 0 citations· 8 references
TL;DR
Simulation results show that while CNNs offer a favorable trade-off between linearization performance and model complexity, GRU and LSTM architectures achieve the best overall NMSE and ACPR improvements, albeit with a higher number of parameters.
Abstract
In this study, we examine and contrast the effectiveness of different artificial neural network (ANN) topologies for power amplifier (PA) digital pre-distortion (DPD). In particular, we investigate long short-term memory (LSTM) networks, gated recurrent units (GRU), recurrent neural networks (RNN), con-volutional neural networks (CNN), and fully connected neural networks (DNN). For training and assessment, a dataset comprising measured input and output signals from a commercial NXP Doherty PA working in the 3.6–3.8 GHz region with a 16-QAM OFDM signal is utilised. Normalised mean squared error (NMSE), adjacent channel power ratio (ACPR), and model complexity are used to evaluate the models. Simulation results show that while CNNs offer a favorable trade-off between linearization performance and model complexity, GRU and LSTM architectures achieve the best overall NMSE and ACPR improvements, albeit with a higher number of parameters. Power spectral density and AM/AM characteristic analyses further confirm the superior linearization performance achieved using recurrent gated structures.
This work proposes a low-complexity Feature Selection NN DPD architecture that employs an offline feature-engineering pipeline based on the Least Absolute Shrinkage and Selection Operator and the Minimum Redundancy Maximum Relevance algorithm to construct a compact and informative input representation.
Cel Thys, Rodney Martinez Alonso, A. Alsarraf et al.· 0 citations
This work presents a direct-learning architecture of a neural network (NN) digital predistortion (DPD) linearizer for a multiple-input multiple-output (MIMO) system while maintaining low complexity compared to a single-input single-output (SISO) system.
In this paper, a behavioral model integrating the grey wolf optimizer (GWO) and a multi-head attention (MA) based bidirectional long short-term memory (BiLSTM) network (GWO-MA-BiLSTM) is proposed for digital predistortion (DPD) of doherty power amplifiers (DPA) in radio-over-fiber communication systems. Unlike other BiLSTM based models, GWO-MA-BiLSTM significantly reduces model training time by leveraging the grey wolf optimizer algorithm to identify the optimal combination of network architecture and hyperparameters. The multi-head attention mechanism enables the model to selectively pay attention to the input signals at different moments. This enables the model to dynamically adjust the attention at different times, so as to better capture important features and dependencies, and improve the performance and accuracy of the model. To verify the modeling ability of the GMO-MA-BiLSTM model for the nonlinearity and memory effect of PA, this paper conducts behavioral modeling of the dynamic AM/AM characteristics, dynamic AM/PM characteristics and PSD of the DPA circuit. The experimental results show that the model prediction data is in good agreement with the circuit simulation data.
Unknown authors· European Conference on Elect...· 0 citations
The analysis demonstrates that the RL-based approach, enabled by an effective neural network initialization strategy, surpasses traditional methods and ML-based DPD schemes such as DLA and ILA and provides a scalable and efficient solution for compensating pattern-dependent nonlinearities in high-speed optical communications.
Arash Rabiepoor, L. Rusch, Ming Zeng· IEEE Open Journal of the Com...· 0 citations
Digital predistortion (DPD) compensates for nonlinear distortions caused by RF power amplifiers (PAs) for efficient and linear signal transmission. Although generalized memory polynomial (GMP) models are frequently used for DPD, their dimensionality increases with memory depth, which raises computational costs and deteriorates numerical conditioning. Although batch principal component analysis (PCA) reduce this dimensionality, it is unable to adjust to PA characteristics that change over time. We present IPCA-GMP, a framework that combines GMP modelling with incremental PCA (IPCA), where updating mean and covariance estimates recursively and executing rank one eigenspace updates from streaming data. The eigenspace update achieves $\mathcal{O}\left(k D^{2}\right)$ per block cost without a complete eigen decomposition by using a rank one perturbation procedure on the current eigen basis. The results demonstrate that IPCA-GMP compresses the model dimension from $D=224$ to $k=20 (11 \times$ compression), achieving a normalized mean square error of -39.02 dB within 0.41, dB of the full GMP baseline. The condition number is better than $3.3 \times 10^{26}$ to 1,570, and with just 1.8% FLOP overhead compared to the baseline GMP solver, the per-update complexity drops from $\mathcal{O}\left(N D^{2}+D^{3}\right)$ (batch PCA) to $\mathcal{O}\left(D^{2}+k D^{2}\right)$.
Girish Chandra Tripathi, Anindya Saha· International Conference on...· 0 citations
This article proposes a novel, low-rate digital predistortion (DPD) for sub-6-GHz 400-MHz modulated signal transmission. In this model, a low-rate input signal is concurrently fed into multiple parallel cascaded model branches to generate the low-rate predistorted signal. Each branch contains: a dual-function finite impulse response (FIR) filter for interpolation and memory effect compensation, multiple parallel Volterra series-based submodels that are selectively activated based on the current input state and are optimized in complexity by a pruning algorithm, and low-rate filters. Additionally, a model parameter extraction method is introduced for this model. Based on this model, a high-precision DPD system can be obtained with low system processing rates. Experimental validation was performed using 5G new radio (NR) signals with 400-MHz modulation bandwidth on a 3.4–3.8-GHz gallium nitride (GaN) Doherty power amplifier (PA) at low system processing rates of 983 and 491 MSPS, respectively. Measurement results demonstrated that the proposed technique achieves good performance with lower complexity than existing models, with a normalized mean-square error (NMSE) and an adjacent channel power ratio (ACPR) of approximately −41 dB and −46 dBc at 983 MSPS, respectively, and an NMSE of approximately −40 dB at 491 MSPS.
Xiaoyu Lu, Tong Tong, Yucheng Yu et al.· IEEE transactions on microwa...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
