AI 中文总结
针对通信带宽增加致数字预失真算法复杂度上升的问题，提出低复杂度特征选择NN DPD架构，用LASSO和MRMR算法构建输入表示，利用实测数据集证明该方法在保持性能时可降低30%计算复杂度。
AI 中文摘要
由于通信带宽不断增加以及高效但非线性功率放大器的使用，数字预失真（DPD）算法变得越来越复杂。特别是，基于神经网络（NN）的DPD方法，使用相位归一化NN架构，通常比广泛部署的基于多项式的方法，如记忆多项式（MP）和广义记忆多项式（GMP）模型，产生更高的计算成本。为弥合研究性能与实际实现之间的差距，我们提出了一种低复杂度特征选择NN DPD架构。该方法采用基于最小绝对收缩和选择算子（LASSO）和最小冗余最大相关性（MRMR）算法的离线特征工程管道，以构建紧凑且信息丰富的输入表示。使用这项工作中公开发布的实测宽带FR3功率放大器数据集，我们证明在保持可比线性化性能的同时，计算复杂度降低了30%。
英文摘要
Due to the continuous increase in communication bandwidth and the use of highly efficient yet nonlinear power amplifiers, Digital Predistortion (DPD) algorithms are becoming increasingly complex. In particular, neural network (NN) based DPD approaches using Phase-Normalized NN architectures often incur substantially higher computational costs than widely deployed polynomial-based methods, such as the Memory Polynomial (MP) and Generalized Memory Polynomial (GMP) models. To bridge this gap between research performance and practical implementation, we propose a low-complexity Feature Selection NN DPD architecture. The proposed method employs an offline feature-engineering pipeline based on the Least Absolute Shrinkage and Selection Operator (LASSO) and the Minimum Redundancy Maximum Relevance (MRMR) algorithm to construct a compact and informative input representation. Using measured wideband FR3 power amplifier datasets that are publicly released with this work, we demonstrate up to 30% reduction in computational complexity while maintaining comparable linearization performance.
CommentsSubmitted to 2026 IEEE Workshop on Signal Processing Systems (SiPS)
