Particle swarm optimization assisted B-spline neural network based predistorter design to enable transmit precoding for nonlinear MIMO downlink

For the multiple-input multiple-output (MIMO) downlink employing high-order quadrature amplitude modulation signaling and with nonlinear high power amplifiers (HPAs) at base station transmitter, existing precoding designs relying on linear MIMO channel can no longer work. We propose an efficient accurate predistorter design to enable transmit for downlink. Specifically, we obtain closed-form least squares estimates of HPA’s phase response using two B-spline neural networks during training. The estimated automatically yields estimate predistorter’s response. Based network response, construct a model adopt particle swarm optimization (PSO) algorithm solve this highly problem. Using our pre-compensate distortions HPAs, standard full-digital readily be adopted combat interference. A simulation study is conducted demonstrate effectiveness proposed PSO assisted design.