A Comparison of Surrogate Behavioral Models for Power Amplifier Linearization under High Sparse Data

• Published in: Sensors (Basel, Switzerland) Vol. 22; no. 19; p. 7461
• Main Authors: Galaviz-Aguilar, Jose Alejandro, Vargas-Rosales, Cesar, Cárdenas-Valdez, José Ricardo, Aguila-Torres, Daniel Santiago, Flores-Hernández, Leonardo
• Format: Journal Article
• Language: English
• Published: Switzerland MDPI AG 01.10.2022; MDPI
• Subjects: Accuracy; Algorithms; Amplifiers, Electronic; behavioral modeling; Comparative analysis; Complexity; Decision trees; Digital integrated circuits; Distribution functions; Equipment Design; Field programmable gate arrays; Linearization; linearization model; Machine learning; Methods; Model accuracy; Modelling; Neural networks; nonlinear modeling; Orthogonal Frequency Division Multiplexing; power amplifier; Power amplifiers; Quadrature amplitude modulation; Receivers & amplifiers; Mexico; power amplifier; nonlinear modeling; behavioral modeling; machine learning; linearization model
• ISSN: 1424-8220; 1424-8220
• DOI: 10.3390/s22197461

A good approximation to power amplifier (PA) behavioral modeling requires precise baseband models to mitigate nonlinearities. Since digital predistortion (DPD) is used to provide the PA linearization, a framework is necessary to validate the modeling figures of merit support under signal conditioning and transmission restrictions. A field-programmable gate array (FPGA)-based testbed is developed to measure the wide-band PA behavior using a single-carrier 64-quadrature amplitude modulation (QAM) multiplexed by orthogonal frequency-division multiplexing (OFDM) based on long-term evolution (LTE) as a stimulus, with different bandwidths signals. In the search to provide a heuristic target approach modeling, this paper introduces a feature extraction concept to find an appropriate complexity solution considering the high sparse data issue in amplitude to amplitude (AM-AM) and amplitude to phase AM-PM models extraction, whose penalties are associated with overfitting and hardware complexity in resulting functions. Thus, experimental results highlight the model performance for a high sparse data regime and are compared with a regression tree (RT), random forest (RF), and cubic-spline (CS) model accuracy capabilities for the signal conditioning to show a reliable validation, low-complexity, according to the peak-to-average power ratio (PAPR), complementary cumulative distribution function (CCDF), coefficients extraction, normalized mean square error (NMSE), and execution time figures of merit. The presented models provide a comparison with original data that aid to compare the dimension and robustness for each surrogate model where (i) machine learning (ML)-based and (ii) CS interpolate-based where high sparse data are present, NMSE between the CS interpolated based are also compared to demonstrate the efficacy in the prediction methods with lower convergence times and complexities.