OpenDPDv2: A Unified Learning and Optimization Framework for Neural Network Digital Predistortion

TL;DR

OpenDPDv2 introduces a unified, energy-efficient neural network framework for digital predistortion in RF systems, combining novel architectures and optimization techniques to maintain performance while reducing power consumption.

Contribution

It presents TRes-DeltaGRU, a lightweight delta-RNN architecture with joint optimization for sparsity and quantization, significantly reducing inference energy in DPD applications.

Findings

Achieves -59.9 dBc ACPR and -42.1 dB EVM with FP32 model.

Reduces inference energy by 4.5x with 56% sparsity.

Maintains high linearization performance with optimized quantization and sparsity.

Abstract

Neural network (NN)-based Digital Predistortion (DPD) has demonstrated superior performance in improving signal quality in wideband radio frequency (RF) power amplifiers (PAs) employing complex modulation. However, NN DPDs usually rely on a large number of parameters for effective linearization and can significantly contribute to the energy consumption of the digital back-end in RF systems. This paper presents OpenDPDv2, an open-source, end-to-end framework that unifies PA modeling, NN-DPD learning, and deployment-oriented model optimization to reduce inference energy while preserving linearization performance. OpenDPDv2 introduces TRes-DeltaGRU, a delta-RNN DPD architecture with a lightweight temporal residual path that improves robustness under aggressive temporal sparsity, and it supports joint optimization of temporal sparsity and fixed-point quantization. On a 3.5 GHz GaN Doherty PA driven by a TM3.1a 200 MHz 256-QAM OFDM signal, the FP32 TRes-DeltaGRU model achieves ACPR of -59.9 dBc and EVM of -42.1 dB. By combining quantization with dynamic temporal sparsity, the model reduces inference energy by 4.5x while maintaining -51.8 dBc ACPR and -35.2 dB EVM at 56% temporal sparsity. Code, datasets, and documentation are publicly available at https://github.com/lab-emi/OpenDPD.