OpenDPDv2统一神经网络射频功率放大器线性化与部署优化，提升效率并降低功耗。
OpenDPDv2: A Unified Learning and Optimization Framework for Neural Network Digital Predistortion
- 提出TRes-DeltaGRU架构，通过轻量时序残差路径应对强时间稀疏性
- 在56%时间稀疏下仍保持-51.8 dBc ACPR和-35.2 dB EVM性能
- 支持定点量化联合优化，推理能耗降低4.5倍，适合边缘部署
基于神经网络的数字预失真（NN-DPD）可有效提升宽带射频功率放大器（PA）的线性化性能，但常增加数字后端复杂度。本文提出OpenDPDv2，一个开源端到端框架，统一了功率放大器建模、神经网络预失真学习与面向部署的优化。该框架引入时序残差（TRes）-Delta门控循环单元（DeltaGRU），一种带轻量时序残差路径的增量式RNN预失真架构，可在极端时间稀疏条件下保持鲁棒性，并支持与定点量化联合优化。在3.5 GHz GaN Doherty PA上，采用TM3.1a 200 MHz 256-QAM OFDM信号测试，FP32精度的TRes-DeltaGRU模型实现-59.9 dBc邻道功率比（ACPR）和-42.1 dB误差向量幅度（EVM）。在56%时间稀疏及W12A12量化下，仅需450个活跃参数，仍维持-51.8 dBc ACPR与-35.2 dB EVM。基于Gem5的时序精确评估显示，该部署优化点前向传播能耗降低4.5倍。代码、数据集与文档已公开于https://github.com/lab-emi/OpenDPD。
原文摘要 · Abstract (English)
Neural network (NN)-based Digital Predistortion (DPD) improves linearization for wideband radio frequency (RF) power amplifiers (PAs) but often increases the complexity of the digital back-end. This paper presents OpenDPDv2, an open-source end-to-end framework that unifies PA modeling, NN-DPD learning, and deployment-oriented optimization. OpenDPDv2 introduces temporal residual (TRes)-Delta Gated Recurrent Unit (DeltaGRU), a delta-RNN DPD architecture with a lightweight temporal residual path for robust operation under aggressive temporal sparsity, and supports joint optimization with 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 -59.9 dBc Adjacent Channel Power Ratio (ACPR) and -42.1 dB Error Vector Magnitude (EVM). With 56% temporal sparsity and W12A12 quantization, the model uses 450 active parameters while maintaining -51.8 dBc ACPR and -35.2 dB EVM. Timing-accurate Gem5-based evaluation further indicates a 4.5x reduction in forward-pass energy for this deployment-oriented operating point. Code, datasets, and documentation are publicly available at https://github.com/lab-emi/OpenDPD.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。