One-step model extraction method for direct learning digital predistortion

A one-step model extraction method is proposed for direct learning (DL) digital predistortion (DPD) system. The expected predistortion signal of the training sequence is first derived by iterative injection of the baseband distortion components, which enables one-step model extraction of the DPD model by least squares estimation afterwards. Compared with the conventional model extraction method for DL DPD, the proposed method yields comparable linearisation performance but has much lower computational complexity.