通过挖掘RNN动态时间稀疏性，实现高效宽带数字预失真。
DeltaDPD: Exploiting Dynamic Temporal Sparsity in Recurrent Neural Networks for Energy-Efficient Wideband Digital Predistortion
- 利用输入信号与隐藏状态的动态时间稀疏性减少计算量。
- 在52%时间稀疏下仍保持ACPR -50.03 dBc、NMSE -37.22 dB性能。
- 适合高带宽射频系统部署，显著降低推理功耗。
数字预失真（DPD）是提升宽带射频功率放大器（PA）信号质量的常用技术。随着带宽和数据速率增加，现役DPD模型依赖循环神经网络（RNN），其计算复杂度制约了系统能效。本文提出DeltaDPD，挖掘输入信号与神经元隐藏状态在时间维度上的动态稀疏性，以减少算术运算和内存访问，同时保持良好线性化性能。在3.5 GHz GaN Doherty PA上使用TM3.1a 200MHz-BW 256-QAM OFDM信号测试，当达到52%时间稀疏时，实现ACPR -50.03 dBc、NMSE -37.22 dB、EVM -38.52 dBc，且估计推理功耗降低1.8倍。代码将在正式发表后于https://www.opendpd.com 开放。
原文摘要 · Abstract (English)
Digital Predistortion (DPD) is a popular technique to enhance signal quality in wideband RF power amplifiers (PAs). With increasing bandwidth and data rates, DPD faces significant energy consumption challenges during deployment, contrasting with its efficiency goals. State-of-the-art DPD models rely on recurrent neural networks (RNN), whose computational complexity hinders system efficiency. This paper introduces DeltaDPD, exploring the dynamic temporal sparsity of input signals and neuronal hidden states in RNNs for energy-efficient DPD, reducing arithmetic operations and memory accesses while preserving satisfactory linearization performance. Applying a TM3.1a 200MHz-BW 256-QAM OFDM signal to a 3.5 GHz GaN Doherty RF PA, DeltaDPD achieves -50.03 dBc in Adjacent Channel Power Ratio (ACPR), -37.22 dB in Normalized Mean Square Error (NMSE) and -38.52 dBc in Error Vector Magnitude (EVM) with 52% temporal sparsity, leading to a 1.8X reduction in estimated inference power. The DeltaDPD code will be released after formal publication at https://www.opendpd.com.
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。