A Low-Sampling-Rate Digital Predistortion Method Based on Inverse Filter Signal Recovery for Wideband Power Amplifiers

Abstract

To address the high cost associated with using high-speed and large-acquisition-bandwidth analog-to-digital-converters (ADCs) in the feedback path, a new low-sampling-rate digital predistortion (DPD) method is proposed in this paper. To model the analog bandpass filter (BPF) in the feedback path, a training method for digital finite impulse response (FIR) filter coefficients in a practical band-limited DPD system is proposed, and a filter matrix is constructed in different forms in the case of continuous signal and cyclic signal inputs. The filter matrix provides an extra degree of band-limited power amplifier (PA) model accuracy and robustness. Then, an inverse filter signal recovery (IFSR) method is proposed to recover the full-band output signal of the PA, which can be used to train the predistorter using conventional DPD techniques. Simulation results validates the effectiveness of the IFSR method, demonstrating that the IFSR-DPD method can reduce the ADC sampling rate to 1/10 or less compared to full-rate sampling methods, and decrease the ADC acquisition bandwidth to about 0.3 times that of the original input signal bandwidth. The linearization performance of the IFSR-DPD method is also evaluated on an instrument-based test platform. When the passband and transition band characteristics of the BPF are unsatisfactory, the proposed low-sampling rate DPD method improves the adjacent channel power ratio (ACPR) by 18.67 dB and the error vector magnitude (EVM) by 1.214%, compared to the scenario without DPD.