MP-DPD: Low-Complexity Mixed-Precision Neural Networks for Energy-Efficient Digital Predistortion of Wideband Power Amplifiers
Yizhuo Wu (TU Delft - Electronics)
A. Li (TU Delft - Electronics)
M. R. Beikmirza (TU Delft - Electronics)
Gagan Deep Singh (TU Delft - Electronics)
Leonardus de Vreede (TU Delft - Electronics)
M. S. Alavi (TU Delft - Electronics)
C. Gao (TU Delft - Electronics)
Qinyu Chen (Universiteit Leiden)
More Info
expand_more
Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.
Abstract
Digital predistortion (DPD) enhances signal quality in wideband radio frequency (RF) power amplifiers (PAs). As signal bandwidths expand in modern radio systems, DPD's energy consumption increasingly impacts overall system efficiency. Deep neural networks (DNNs) offer promising advancements in DPD, yet their high complexity hinders their practical deployment. This article introduces open-source mixed-precision (MP) neural networks that employ quantized low-precision fixed-point parameters for energy-efficient DPD. This approach reduces computational complexity and memory footprint, thereby lowering power consumption without compromising linearization efficacy. Applied to a 160-MHz-BW 1024-QAM OFDM signal from a digital RF PA, MP-DPD gives no performance loss against 32-bit floating-point precision DPDs, while achieving -43.75 (L)/-45.27 (R) dBc in the adjacent channel power ratio (ACPR) and -38.72 dB in error vector magnitude (EVM). A 16-bit fixed-point-precision MP-DPD enables a 2.8× reduction in estimated inference power. The DPD code in PyTorch is publicly available on GitHub.