Embedded updating system based on integrated NNs in order to achieve adaptative predistortion of nonlinear HPA characteristics

In order to correct non-linearities due to high power amplifiers (HPA) operating near saturation in telecommunication transceivers, a new adaptative predistortion system based on neural networks (NNs) was developed. For size, consumption and bandwidth purposes, the multi-layer perceptron (MLP) type NNs were implemented in a 0.6μm CMOS ASIC. The NNs parameters are updated with a computer as a function of the simulation conditions (temperature drifts, ageing variations). The interface between the analog part and the software updating system is integrated in a digital board containing a FPGA, six analog-to-digital converters and sixty-two digital-to-analog converters. This paper describes the realization of each part of the system and presents experimental results.