Inverse Design of Compact and Wideband Inverted Doherty Power Amplifiers Using Deep Learning
For RF engineers designing Doherty power amplifiers, this work provides a novel automated design method that integrates multiple functions into a single compact structure, though it is an incremental application of existing deep learning techniques to a specific domain.
This paper uses deep learning (CNNs and genetic algorithms) to inversely design a compact, wideband inverted Doherty power amplifier, achieving 51%-63% peak drain efficiency and 48%-54% 6-dB back-off efficiency over 1.9-2.5 GHz, with output power of 44±0.3 dBm and ACLR better than -53.2 dBc after DPD.
This paper presents a deep learning-assisted methodology for the inverse synthesis of a compact, wideband inverted Doherty power amplifier (PA). Convolutional neural networks (CNNs) and genetic algorithms (GAs) are jointly employed to generate pixelated Doherty combiner networks that integrate load modulation, impedance matching, power combining, and phase compensation into a single structure. As a proof of concept, we design and fabricate a GaN HEMT Doherty PA with a pixelated output combiner. The prototype achieves a measured peak drain efficiency of 51%-63% and a 6-dB back-off efficiency of 48%-54% over 1.9-2.5 GHz. Within the same frequency range, the measured output power is 44+/-0.3 dBm. Furthermore, with digital predistortion (DPD) applied, the prototype circuit demonstrates an adjacent channel leakage ratio (ACLR) better than -53.2 dBc.