A Novel Power Amplifier Behavior Modeling Based on RBF Neural Network with Chaos Particle Swarm Optimization Algorithm

Abstract

In order to design and optimize high-linearity power amplifier (PA), which with nonlinear and memory effect, it is very important to build power amplifier behavior modeling accurately. This paper proposes a power amplifier behavior modeling based on RBF neural network with improved chaos particle swarm optimization algorithm. To make the particles evenly distribute in the problem search space, a novel Chaos Particle Swarm Optimization (CPSO) is proposed based on the analysis of the ergodicity of chaos and inertia weight of Particle Swarm Optimization (PSO). Based on circle model, the new model is introduced to avoid PSO from getting into local optimum. This paper uses free scale semiconductor chip MRF6S21140 to carry on amplifier circuit design in the ADS and the MATLAB fitting simulation of the extracted data, by improved CPSO-RBF algorithm. Its accuracy is assessed by comparing RBF modeling with voltage RMS error (RMSE), epochs, and fitting time. The result shows that improved CPSO-RBF has better fitting function.