Data-Efficient Bayesian Optimization with Constraints for Power Amplifier Design

Finding the optimal working conditions for non-linear electrical components under large signal stimuli can be challenging, mainly due to the high number of input dimensions and multiple local minima of the goal function. In this paper a Bayesian optimization method is applied in order to limit the number of evaluations by a commercial harmonic balance simulator. The method is applied to amplifier optimization utilizing Wolsfspeed CGH40010F HEMT, for which input power, bias voltages and load at fundamental harmonic frequencies are changed in order to maximize for combined efficiency, gain, and output power. The optimum is found already after 80 iterations.