Digital Predistortion with Compressed Observations for Cloud-Based Learning

Abstract

This paper presents a novel system architecture for digital predistortion (DPD) of power amplifiers (PA), where the training of the DPD model is done in a remote compute infrastructure i.e. cloud or a distributed unit (DU). In beyond-5G systems it is no longer feasible to perform computationally intensive tasks such as DPD training locally in the radio unit front-end which has stringent power consumption requirements. Thus, we propose to split the DPD system and perform the compute-intensive DPD training in the DU where more processing resources are available. To enable the distant training, the observed PA output, i.e. the observation signal, must be available, however, sending the data-intensive observation signal to the DU adds additional communication overhead to the system. In this paper, a low-complexity compression method is proposed to reduce the bit-resolution of the observation signal by removing the known linear part in the observation to use fewer bits to represent the remaining information. Our numerical simulations show a reduction of 50 % of bits/samples for the accurate training of the DPD model. The DPD performance was evaluated based on simulation for a strongly driven PA operated at 28 GHz with a 200 MHz wide OFDM signal.