Augmented Iterative Learning Control for Neural-Network-Based Joint Crest Factor Reduction and Digital Predistortion of Power Amplifiers

Wang, Siqi; Roger, Michel; Sarrazin, Julien; Lelandais-Perrault, Caroline

doi:10.1109/tmtt.2020.3011152

Cited by 18 publications

(13 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The developed algorithm is dependent on the digital domain, unlike the other reported works [ 26 , 28 ]; these approaches are based mainly on vector signal generator (VSG), or vector signal transceiver to generate the I/Q baseband data samples [ 18 , 24 ], which is more expensive test equipment, and the signals are predefined. In this context, our proposed CFR-clipping system can be fully controlled for LTE 5-MHz and LTE 10-MHz applications, from 47-MHz to 6-GHz.…”

Section: Resultsmentioning

confidence: 99%

“…Ref. [ 18 ] explores clipping and filtering applied to single-carrier and two-carrier 20-MHz LTE signals as the stimulus, the developed CFR technique improves the spectral regrowth using a testbench of a device under test (DUT) operating at 3.3–3.8 GHz. This work focuses on the design and implementation stage of a transceiver that operates in the 2 GHz band for LTE applications.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A Crest Factor Reduction Technique for LTE Signals with Target Relaxation in Power Amplifier Linearization

Cárdenas-Valdez

Galaviz-Aguilar

Vargas-Rosales

et al. 2022

Sensors

View full text Add to dashboard Cite

The signal conditioning treatment to achieve good relation of power with radio-frequency (RF) conversion in conventional transceiver systems require precise baseband models. A developed framework is built to provide a demonstration of the modeling figures of merit with orthogonal frequency division multiplexing (OFDM) support under signal conditioning and transmission restrictions to waveforms with high peak to average power ratio (PAPR) in practical applications. Therefore, peak and average power levels have to be limited to correct high PAPR for a better suited correction power from the amplifier that can lead to compression or clipping in the signal of interest. This work presents an alternative joint crest factor reduction (CFR) algorithm to correct the performance of PAPR. A real-time field-programmable gate array (FPGA) testbed is developed to characterize and measure the behavior of an amplifier using a single-carrier 64–QAM OFDM based on long-term evolution (LTE) downlink at 2.40 GHz as stimulus, across wide modulation bandwidths. The results demonstrate that the CFR accuracy capabilities for the signal conditioning show a reliable clipping reduction to give a smooth version of the clipping signal and provide a factor of correction for the unwanted out-of-band emission validated according to the adjacent channel power ratio (ACPR), PAPR, peak power, complementary cumulative distribution function (CCDF), and error vector magnitude (EVM) figures of merit.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

A Crest Factor Reduction Technique for LTE Signals with Target Relaxation in Power Amplifier Linearization

Cárdenas-Valdez

Galaviz-Aguilar

Vargas-Rosales

et al. 2022

Sensors

View full text Add to dashboard Cite

show abstract

“…Various ANN modeling and design methods for power amplifiers have been introduced, e.g., [89], [90], [108], [122], [129], [138], [139], [142], [178], [179], [180], [181]. Related to power amplifier design, ANN has also been used in digital predistortion, e.g., [182], [183], [184], [185], [186].…”

Section: B Behavioral Modeling Of Nonlinear Circuitsmentioning

confidence: 99%

Artificial Neural Networks for Microwave Computer-Aided Design: The State of the Art

Feng

Jin

et al. 2022

IEEE Trans. Microwave Theory Techn.

View full text Add to dashboard Cite

This article presents an overview of artificial neural network (ANN) techniques for a microwave computer-aided design (CAD). ANN-based techniques are becoming useful for performing forward/inverse modeling for active/passive components to enhance a circuit design. With measured or simulated data of microwave devices, ANNs can be trained to learn relevant microwave relationships, which are, otherwise, computationally expensive or for which efficient analytical formulas are not available. Fundamental concepts of the ANN structure and training, such as feedforward neural networks (FFNNs), recurrent neural networks (RNNs)/dynamic neural networks (DNNs)/time-delay neural networks (TDNNs), deep neural networks, and neural network training and extrapolation, are described. Knowledgebased neural networks (KBNNs) are described for improving the accuracy and reliability of modeling and design optimization. Various advanced ANN techniques, such as neuro-transfer function (neuro-TF) modeling, neural network inverse modeling, and deep neural network modeling, are discussed. The existing and emerging applications of ANN in microwave CAD are identified, such as electromagnetic (EM)/multiphysics modeling, modeling of nonlinear circuits and transistors, filter design, very largescale integration (VLSI) interconnects, oscillator, transmitter and receiver modeling, and CAD applications in such as gallium nitride (GaN) high electron-mobility transistor (HEMT), wireless power transfer (WPT), microelectromechanical system (MEMS), and substrate-integrated waveguide (SIW).

show abstract

“…However, these improvements come with a disadvantage in terms of complexity. Additional computation is required to achieve the perfect signal before any training for ANN occurs when using ILC [17], whereas in the case of DLA, the additional complexity can go as far as requiring a separate PA model ANN. This ANN, after it is trained, is used as a source of error gradients for training the DPD model [18], which significantly increases the amount of computation required.…”

Section: Spline Activation Functionmentioning

confidence: 99%

Segmented Spline Curve Neural Network for Low Latency Digital Predistortion of RF Power Amplifiers

Vaicaitis

Dooley

2022

IEEE Trans. Microwave Theory Techn.

View full text Add to dashboard Cite

At present, we are the dawn of a new era for wireless communication systems. The new dynamic approach to the operation of cellular networks requires an extension of the essential input-output hardware mechanisms, to include intelligence. Traditional neural network structures can be used to embed artificial intelligence into cellular network base stations; however, standard network structures are not an optimal solution for these use cases. In this article, we present a neural network structure, which is specifically designed to provide a more accurate and computationally efficient solution compared with the previous neural network solutions for predistortion of RF power amplifiers (PAs). The proposed network structure is directly compared with alternative neural network solutions, which have been successfully employed for digital predistortion (DPD). The operation of this network is validated for DPD with experimental measurements with wideband signals using the latest generation of commercially available RF hardware. The novel network structure proposed in this work is demonstrated, in practice, to have better performance for a normalized mean square error (NMSE), an adjacent channel leakage ratio (ACLR), and an error vector magnitude (EVM) compared with the most popular previously published neural network.

show abstract

Augmented Iterative Learning Control for Neural-Network-Based Joint Crest Factor Reduction and Digital Predistortion of Power Amplifiers

Cited by 18 publications

References 41 publications

A Crest Factor Reduction Technique for LTE Signals with Target Relaxation in Power Amplifier Linearization

A Crest Factor Reduction Technique for LTE Signals with Target Relaxation in Power Amplifier Linearization

Artificial Neural Networks for Microwave Computer-Aided Design: The State of the Art

Segmented Spline Curve Neural Network for Low Latency Digital Predistortion of RF Power Amplifiers

Contact Info

Product

Resources

About