Deep Learning-Driven Black-Box Doherty Power Amplifier with Pixelated Output Combiner and Extended Efficiency Range

• URL: http://arxiv.org/abs/2603.16565v1
• Date: Tue, 17 Mar 2026 14:23:58 GMT
• Title: Deep Learning-Driven Black-Box Doherty Power Amplifier with Pixelated Output Combiner and Extended Efficiency Range
• Abstract summary: This article presents a deep learning-driven inverse design methodology for Doherty power amplifiers (PA) with multi-port pixelated output combiner networks.<n>A deep convolutional neural network (CNN) is developed and trained as an electromagnetic (EM) surrogate model.<n>We synthesize complex Doherty combiners that enable an extended back-off efficiency range using fully symmetrical devices.
• Score: 10.090846922590462
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: This article presents a deep learning-driven inverse design methodology for Doherty power amplifiers (PA) with multi-port pixelated output combiner networks. A deep convolutional neural network (CNN) is developed and trained as an electromagnetic (EM) surrogate model to accurately and rapidly predict the S-parameters of pixelated passive networks. By leveraging the CNN-based surrogate model within a blackbox Doherty framework and a genetic algorithm (GA)-based optimizer, we effectively synthesize complex Doherty combiners that enable an extended back-off efficiency range using fully symmetrical devices. As a proof of concept, we designed and fabricated two Doherty PA prototypes incorporating three-port pixelated combiners, implemented with GaN HEMT transistors. In measurements, both prototypes demonstrate a maximum drain efficiency exceeding 74% and deliver an output power surpassing 44.1 dBm at 2.75 GHz. Furthermore, a measured drain efficiency above 52% is maintained at the 9-dB back-off power level for both prototypes at the same frequency. To evaluate linearity and efficiency under realistic signal conditions, both prototypes are tested using a 20-MHz 5G new radio (NR)-like waveform exhibiting a peak-to-average power ratio (PAPR) of 9.0 dB. After applying digital predistortion (DPD), each design achieves an average power added efficiency (PAE) above 51%, while maintaining an adjacent channel leakage ratio (ACLR) better than -60.8 dBc.

Related papers

• Inverse Design of Compact and Wideband Inverted Doherty Power Amplifiers Using Deep Learning [9.885945418536052]
  This paper presents a deep learning-assisted methodology for the inverse synthesis of a compact, wideband inverted Doherty power amplifier (PA)<n>CNNs and genetic algorithms are jointly employed to generate pixelated Doherty combiner networks.<n>As a proof of concept, we design and fabricate a GaN HEMT Doherty PA with a pixelated output combiner.
  arXiv  Detail & Related papers  (2026-06-25T13:19:38Z)
• Deep Learning-Driven Inverse Design of Doherty Power Amplifiers Using Pixelated Combiners and Dual-State Impedance Synthesis [9.885945418536052]
  We propose a three-port Doherty combiner design methodology that combines deep convolutional neural networks (CNNs), pixelated layout representations, and genetic algorithms (GA)<n>As a proof of concept, two GaN HEMT Doherty PA prototypes incorporating three-port pixelated combiners are designed and fabricated.
  arXiv  Detail & Related papers  (2026-06-16T18:38:15Z)
• IIET: Efficient Numerical Transformer via Implicit Iterative Euler Method [59.02943805284446]
  Iterative Implicit Euler Transformer (IIET)<n>IIAD allows users to effectively balance the performance-efficiency trade-off.<n>E-IIET variant achieves an average performance gain exceeding 1.6% over vanilla Transformer with comparable speed.
  arXiv  Detail & Related papers  (2025-09-26T15:14:03Z)
• OpenDPDv2: A Unified Learning and Optimization Framework for Neural Network Digital Predistortion [10.484441707788127]
  This paper presents OpenDPDv2, a unified framework for PA modeling, DPD learning, and model optimization.<n> optimization techniques feature a novel DPD algorithm, TRes-DeltaGRU, alongside two energy-efficient methods.
  arXiv  Detail & Related papers  (2025-07-09T13:54:47Z)
• DPD-NeuralEngine: A 22-nm 6.6-TOPS/W/mm$^2$ Recurrent Neural Network Accelerator for Wideband Power Amplifier Digital Pre-Distortion [9.404504586344107]
  DPD-NeuralEngine is an ultra-fast, tiny-area, and power-efficient DPD accelerator based on a Gated Recurrent Unit (GRU) neural network (NN)<n>Our 22 nm CMOS implementation operates at 2 GHz, capable of processing I/Q signals up to 250 MSps.<n>To our knowledge, this work represents the first AI-based DPD application-specific integrated circuit (ASIC) accelerator.
  arXiv  Detail & Related papers  (2024-10-15T16:39:50Z)
• MP-DPD: Low-Complexity Mixed-Precision Neural Networks for Energy-Efficient Digital Predistortion of Wideband Power Amplifiers [8.58564278168083]
  Digital Pre-Distortion (DPD) enhances signal quality in wideband RF power amplifiers (PAs) This paper introduces open-source mixed-precision (MP) neural networks that employ quantized low-precision fixed-point parameters for energy-efficient DPD.
  arXiv  Detail & Related papers  (2024-04-18T21:04:39Z)
• Function Approximation for Reinforcement Learning Controller for Energy from Spread Waves [69.9104427437916]
  Multi-generator Wave Energy Converters (WEC) must handle multiple simultaneous waves coming from different directions called spread waves. These complex devices need controllers with multiple objectives of energy capture efficiency, reduction of structural stress to limit maintenance, and proactive protection against high waves. In this paper, we explore different function approximations for the policy and critic networks in modeling the sequential nature of the system dynamics.
  arXiv  Detail & Related papers  (2024-04-17T02:04:10Z)
• Broadband parametric amplification in DARTWARS [64.98268713737]
  Traveling-Wave Parametric Amplifiers (TWPAs) may be especially suitable for practical applications due to their multi-Gigahertz amplification bandwidth. The DARTWARS project aims to develop a KITWPA capable of achieving $20,$ dB of amplification. The measurements revealed an average amplification of approximately $9,$dB across a $2,$GHz bandwidth for a KITWPA spanning $17,$mm in length.
  arXiv  Detail & Related papers  (2024-02-19T10:57:37Z)
• Josephson parametric amplifier with Chebyshev gain profile and high saturation [0.0]
  We demonstrate a Josephson parametric amplifier design with a band-pass impedance matching network based on a third-order Chebyshev prototype. We measure eight amplifiers operating at 4.6 GHz that exhibit gains of 20 dB with less than 1 dB gain ripple and up to 500 MHz bandwidth. We characterize the system readout efficiency and its signal-to-noise ratio near saturation using a Sycamore processor.
  arXiv  Detail & Related papers  (2023-05-28T22:04:08Z)
• Readout of a quantum processor with high dynamic range Josephson parametric amplifiers [132.67289832617647]
  Device is matched to the 50 $Omega$ environment with a bandwidth of 250-300 MHz, with input saturation powers up to -95 dBm at 20 dB gain. A 54-qubit Sycamore processor was used to benchmark these devices. Design has no adverse effect on system noise, readout fidelity, or qubit dephasing.
  arXiv  Detail & Related papers  (2022-09-16T07:34:05Z)
• Topological Josephson parametric amplifier array: A proposal for directional, broadband, and low-noise amplification [39.58317527488534]
  Low-noise microwave amplifiers are crucial for detecting weak signals in fields such as quantum technology and radio astronomy. We show that compact devices with few sites can achieve exceptional performance, with gains exceeding 20 dB over a bandwidth ranging from hundreds of MHz to GHz. The device also operates near the quantum noise limit and provides topological protection against up to 15% fabrication disorder.
  arXiv  Detail & Related papers  (2022-07-27T18:07:20Z)
• Towards a Competitive End-to-End Speech Recognition for CHiME-6 Dinner Party Transcription [73.66530509749305]
  In this paper, we argue that, even in difficult cases, some end-to-end approaches show performance close to the hybrid baseline. We experimentally compare and analyze CTC-Attention versus RNN-Transducer approaches along with RNN versus Transformer architectures. Our best end-to-end model based on RNN-Transducer, together with improved beam search, reaches quality by only 3.8% WER abs. worse than the LF-MMI TDNN-F CHiME-6 Challenge baseline.
  arXiv  Detail & Related papers  (2020-04-22T19:08:33Z)
• End-to-End Multi-speaker Speech Recognition with Transformer [88.22355110349933]
  We replace the RNN-based encoder-decoder in the speech recognition model with a Transformer architecture. We also modify the self-attention component to be restricted to a segment rather than the whole sequence in order to reduce computation.
  arXiv  Detail & Related papers  (2020-02-10T16:29:26Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.