MP-DPD: Low-Complexity Mixed-Precision Neural Networks for Energy-Efficient Digital Predistortion of Wideband Power Amplifiers

TL;DR

This paper presents low-complexity mixed-precision neural networks for digital predistortion in wideband power amplifiers, significantly reducing energy consumption while maintaining performance.

Contribution

It introduces open-source mixed-precision neural networks with quantized parameters for energy-efficient DPD in RF systems, achieving comparable performance to high-precision models.

Findings

No performance loss compared to 32-bit models in ACPR and EVM.

Achieves 2.8x reduction in inference power with 16-bit fixed-point MP-DPD.

Reduces computational complexity and memory footprint for practical deployment.

Abstract

Digital Pre-Distortion (DPD) enhances signal quality in wideband 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 paper 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 160MHz-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 Adjacent Channel Power Ratio (ACPR) and -38.72 dB in Error Vector Magnitude (EVM). A 16-bit fixed-point-precision MP-DPD enables a 2.8X reduction in estimated inference power. The PyTorch learning and testing code is publicly available at \url{https://github.com/lab-emi/OpenDPD}.