Deep Learning-Driven Inverse Design of Doherty Power Amplifiers Using Pixelated Combiners and Dual-State Impedance Synthesis
arXiv:2606.18395v1 Announce Type: cross Abstract: The output combiner of a Doherty power amplifier (PA) integrates load modulation, impedance matching, and phase compensation within a single network, making its design and synthesis highly challenging. In this paper, we propose a three-port Doherty combiner design methodology that combines deep convolutional neural networks (CNNs), pixelated layout representations, and genetic algorithms (GA) with dual-state impedance synthesis to address both peak and back-off power conditions. As a proof of concept, two GaN HEMT Doherty PA prototypes incorpor
The increasing demand for efficient power conversion and the maturity of deep learning techniques are converging to address complex engineering challenges.
This development can significantly improve the efficiency and design complexity of RF power amplifiers, crucial components in wireless communication infrastructure.
The design process for Doherty Power Amplifiers (PAs) can become more autonomous, efficient, and capable of optimizing for multiple operating conditions simultaneously.
- · Wireless communication companies
- · RF chip manufacturers
- · Telecommunications infrastructure providers
- · AI/ML in engineering design sector
- · Traditional manual RF design consultancies
More energy-efficient and compact wireless base stations and communication devices.
Reduced operational costs for telecommunication networks due to lower power consumption.
Accelerated development of next-generation wireless standards (e.g., 6G) relying on highly efficient RF front-ends.
This signal links to a primary source. Continuum Brief monitors and indexes it as part of the live intelligence stream — we do not republish source content.
Read at arXiv cs.AI