Machine-Learning Based Digital Doherty Power Amplifier


This paper reports a new architecture of power amplifiers (PA), for which machine learning is applied in real-time to adaptively optimize PA performance. For varying input stimuli such as carrier frequency, bandwidth and power level, developed algorithms can intelligently optimize parameters including bias voltages, input signal phases and power splitting ratios based on a user-defined cost function. Our demonstrator of a wideband GaN Digital Doherty PA achieves significant performance enhancement from 3.0-3.8 GHz, in particular, at high back-off power with approximately 3dB more Gain and 20% higher efficiency compared with analog counterpart. To the authors best knowledge, this is the first reported work of model-free machine learning applied for Doherty PA control. It explores a new area of RF PA optimization, in which accurate analytical models and tedious manual tuning can be avoided.


  • Related News & Events

    •  NEWS    Research on Intelligent Power Amplifier is Cover Story of Microwave Journal
      Date: April 15, 2021
      MERL Contact: Mouhacine Benosman
      Research Areas: Communications, Electronic and Photonic Devices, Machine Learning
      • The cover article in the April issue of Microwave Journal features MERL and MELCO's invited paper entitled "A New Frontier for Power Amplifiers Enabled by Machine Learning". Our recent research applying ML for optimizing operating conditions of advanced power amplifier designs is highlighted.

        Since 1958, Microwave Journal has been the leading source for information about RF and Microwave technology, design techniques, news, events and educational information. Microwave Journal reaches 50,000 qualified readers monthly with a print magazine that has a global reach.
    •  NEWS    Mitsubishi Electric Corporation and MERL Press Release Describes Future Digitally Controlled Power Amplifier
      Date: January 10, 2019
      Where: Tokyo, Japan
      MERL Contacts: Mouhacine Benosman; Philip V. Orlik
      Research Areas: Communications, Electronic and Photonic Devices, Machine Learning, Signal Processing
      • Mitsubishi Electric Corporation announced today its development of the world's first ultra-wideband digitally controlled gallium nitride (GaN) amplifier, which is compatible with a world-leading range of sub-6GHz bands focused on fifth-generation (5G) mobile communication systems. With a power efficiency rating of above 40%, the amplifier is expected to contribute to large-capacity communication and reduce the power consumption of mobile base stations.

        MERL and Mitsubishi Electric researchers collaborated to develop digital control methods for amplifiers achieving high-efficiency of 40% and above, with 110% of the fractional bandwidth over frequency range 1.4-4.8 GHz. The digital control signals are designed using a learning-function based on Maisart®.

        Please see the link below for the full Mitsubishi Electric press release text.
  • Related Video