Predistortion of nonlinear high-power amplifiers using neural networks

This paper presents a new predistortion scheme based on Radial Basis Function (RBF) neural network for high-power amplifier (HPA) with memory in an orthogonal frequency division multiplexing (OFDM) system. An efficient algorithm to update the neural network weights parameters and the centers and widths of RBF is derived. Simulation results show that the proposed neural network predistorter can effectively reduce the bit error rate and adjacent channel interference caused by nonlinear HPA and produce a faster convergence speed than the conventional backpropagation algorithm.