基于多通道IQRD-RLS算法的功率放大器行为模型

A Novel Multichannel IQRD-RLS Algorithm for Behavioral Modeling of Power Amplifiers

使用通用记忆多项式模型来精确地建立射频功率放大器的非线性动态行为模型,模型系数使用多通道IQRD-RLS算法进行提取。IQRD-RLS算法可以直接求解时间递归最小二乘权值向量,避免了在以前直接QR分解方法中所必须的后向迭代过程。且该算法使用Givens旋转操作更新递归的模型系数,比较适合使用脉动阵列实时实现快速的收敛性和良好的数值性能。用ADS仿真数据进行验证,结果表明本模型能够满意地描述宽带射频功率放大器的非线性动态特性。

The goal of this paper is to characterize the nonlinear dynamic behavior of RF power amplifiers using the general memory polynomial（GMP） model whose coefficients are extracted by the multichannel inverse QR decomposition recursive least-squares（IQRD-RLS） algorithms.The IQRD-RLS approach solves directly for the time-recursive least squares weight vector,while avoiding the highly serial backsubstitution step required in previously derived QRD approaches.Furthermore,the approach employs Givens rotation operations to recursively update the model coefficients and is suitable to be implemented using systolic array to achieve fast convergence and good numerical properties.The model is validated by means of ADS simulation data.The result indicates that model is capable of satisfactorily describing the nonlinear dynamic behavior of wideband RF power amplifiers.