High-Efficiency Broadband Doherty Power Amplifier Optimization Based on Genetic Algorithms and Neural Networks

This paper proposes a design method for high-efficiency broadband Doherty power amplifiers (DPAs) optimized through a co-simulation approach combining genetic algorithms and neural networks. The method integrates the global search capability of genetic algorithms with the predictive power of neural networks to efficiently optimize the DPA matching network parameters. Key performance metrics such as output power, efficiency, and gain are incorporated into the objective function for comprehensive optimization. A DPA operating from 1.5 GHz to 2.6 GHz was designed and fabricated. Measurement results demonstrate that the optimized amplifier achieves saturated output power between 42.19 dBm and 44.7 dBm, saturated efficiency from 51.4% to 61.8%, and 6 dB back-off efficiency ranging from 44.3% to 56.4% across the bandwidth. These results verify the feasibility and effectiveness of the proposed optimization method.