Vector Decomposed Long Short-Term Memory Model for Behavioral Modeling and Digital Predistortion for Wideband RF Power Amplifiers

This paper proposes two novel vector decomposed neural network models for behavioral modeling and digital predistortion (DPD) of radio-frequency (RF) power amplifiers (PAs): vector decomposed long short-term memory (VDLSTM) model and simplified vector decomposed long short-term memory (SVDLSTM) model. The proposed VDLSTM model is a variant of the classic long short-term memory (LSTM) model that can model long-term memory effects. To comply with the physical mechanism of RF PAs, VDLSTM model only conducts nonlinear operations on the magnitudes of the input signals, while the phase information is recovered by linear weighting operations on the output of the LSTM cell. Furthermore, this study modifies the LSTM cell by adding phase recovery operations inside the cell and replacing the original hidden state with the output magnitudes that are recovered with phase information. With the modified LSTM cell, a low-complexity SVDLSTM model is proposed. The experiment results show that the proposed VDLSTM model can achieve better linearization performance compared with the state-of-the-art models when linearizing PAs with wideband inputs. Besides, in wideband scenarios, SVDLSTM model with much fewer parameters can present comparable linearzation performance compared to VDLSTM model.

[1]  Yue Li,et al.  Vector Decomposition Based Time-Delay Neural Network Behavioral Model for Digital Predistortion of RF Power Amplifiers , 2019, IEEE Access.

[2]  M. Jaidane-Saidane,et al.  Adaptive digital/RF predistortion using a nonuniform LUT indexing function with built-in dependence on the amplifier nonlinearity , 2004, IEEE Transactions on Microwave Theory and Techniques.

[3]  Guan Gui,et al.  Behavioral Modeling and Linearization of Wideband RF Power Amplifiers Using BiLSTM Networks for 5G Wireless Systems , 2019, IEEE Transactions on Vehicular Technology.

[4]  AKHIL GUPTA,et al.  A Survey of 5G Network: Architecture and Emerging Technologies , 2015, IEEE Access.

[5]  Anding Zhu,et al.  Instantaneous Sample Indexed Magnitude-Selective Affine Function-Based Behavioral Model for Digital Predistortion of RF Power Amplifiers , 2018, IEEE Transactions on Microwave Theory and Techniques.

[6]  Zoya Popovic,et al.  Amping Up the PA for 5G: Efficient GaN Power Amplifiers with Dynamic Supplies , 2017, IEEE Microwave Magazine.

[7]  Peng Chen,et al.  Behavioral Modeling of GaN Power Amplifiers Using Long Short-Term Memory Networks , 2018, 2018 International Workshop on Integrated Nonlinear Microwave and Millimetre-wave Circuits (INMMIC).

[8]  F.M. Ghannouchi,et al.  Twin Nonlinear Two-Box Models for Power Amplifiers and Transmitters Exhibiting Memory Effects With Application to Digital Predistortion , 2009, IEEE Microwave and Wireless Components Letters.

[9]  Guigang Zhang,et al.  Deep Learning , 2016, Int. J. Semantic Comput..

[10]  F.M. Ghannouchi,et al.  Adaptive Digital Predistortion of Wireless Power Amplifiers/Transmitters Using Dynamic Real-Valued Focused Time-Delay Line Neural Networks , 2010, IEEE Transactions on Microwave Theory and Techniques.

[11]  Arif Ahmed,et al.  Efficient PA modeling using neural network and measurement setup for memory effect characterization in the power device , 2005, IMS 2005.

[12]  Pere L. Gilabert,et al.  Order reduction of wideband digital predistorters using principal component analysis , 2013, 2013 IEEE MTT-S International Microwave Symposium Digest (MTT).

[13]  F.M. Ghannouchi,et al.  Dynamic behavioral modeling of 3G power amplifiers using real-valued time-delay neural networks , 2004, IEEE Transactions on Microwave Theory and Techniques.

[14]  J. C. Pedro,et al.  A Physically Meaningful Neural Network Behavioral Model for Wireless Transmitters Exhibiting PM–AM/PM–PM Distortions , 2011, IEEE Transactions on Microwave Theory and Techniques.

[15]  Keiichi Yamaguchi,et al.  Deep Neural Network-Based Digital Predistorter for Doherty Power Amplifiers , 2019, IEEE Microwave and Wireless Components Letters.

[16]  Sandeep Subramanian,et al.  Deep Complex Networks , 2017, ICLR.

[17]  F Mkadem,et al.  Physically Inspired Neural Network Model for RF Power Amplifier Behavioral Modeling and Digital Predistortion , 2011, IEEE Transactions on Microwave Theory and Techniques.

[18]  Jürgen Schmidhuber,et al.  Long Short-Term Memory , 1997, Neural Computation.

[19]  A Memory Term Reduction Approach for Digital Pre-Distortion Using the Attention Mechanism , 2019, IEEE Access.

[20]  Jaehyeong Kim,et al.  A Generalized Memory Polynomial Model for Digital Predistortion of RF Power Amplifiers , 2006, IEEE Transactions on Signal Processing.

[21]  F.M. Ghannouchi,et al.  Behavioral modeling and predistortion , 2009, IEEE Microwave Magazine.

[22]  Christian Fager,et al.  Iterative Learning Control for RF Power Amplifier Linearization , 2016, IEEE Transactions on Microwave Theory and Techniques.

[23]  Fadhel M. Ghannouchi,et al.  Composite Neural Network Digital Predistortion Model for Joint Mitigation of Crosstalk, $I/Q$ Imbalance, Nonlinearity in MIMO Transmitters , 2018, IEEE Transactions on Microwave Theory and Techniques.

[24]  Fadhel M. Ghannouchi,et al.  Augmented Real-Valued Time-Delay Neural Network for Compensation of Distortions and Impairments in Wireless Transmitters , 2019, IEEE Transactions on Neural Networks and Learning Systems.

[25]  Jeffrey G. Andrews,et al.  What Will 5G Be? , 2014, IEEE Journal on Selected Areas in Communications.

[26]  Dennis R. Morgan,et al.  A robust digital baseband predistorter constructed using memory polynomials , 2004, IEEE Transactions on Communications.

[27]  A. Zhu.  Decomposed Vector Rotation-Based Behavioral Modeling for Digital Predistortion of RF Power Amplifiers , 2015, IEEE Transactions on Microwave Theory and Techniques.