Dynamic Behavioral Modeling of RF Power Amplifier Based on Time-Delay Support Vector Regression
Dynamic Behavioral Modeling of RF Power Amplifier Based on Time-Delay Support Vector Regression
复制标题
基于时滞支持向量回归的射频功率放大器动态行为建模
DOI：
10.1109/tmtt.2018.2884414
复制
发表时间：
2019-02-01
影响因子：
4.3
通讯作者：
King, Justin B.
中科院分区：
文献类型：
--
作者：
Cai, Jialin;Yu, Chao;King, Justin B.
提出了一种基于时滞支持向量回归（SVR）的动态行为建模方法。作为一种先进的机器学习算法，支持向量回归（SVR）方法为射频功率放大器（PA）的行为建模提供了一种有效的选择，同时考虑了器件非线性和记忆的影响。提出的建模技术的基本理论，沿着详细的模型提取过程。与传统的人工神经网络（ANN）技术，这需要时间来确定最佳配置的模型，支持向量回归机方法可以在很短的时间内获得最优模型，使用网格搜索技术。最后给出了一个应用于射频功率放大器的最优支持向量回归模型选择的例子，与默认支持向量回归模型相比，所选模型的性能有了很大的提高。使用LDMOS PA、单器件氮化镓（GaN）PA和Doherty GaN PA进行了实验验证，表明新的建模方法提供了非常有效和非常准确的预测。与传统的沃尔泰拉模型、规范分段线性模型和基于人工神经网络的模型相比，该模型在保持合理复杂度的前提下提高了性能。此外，它表明，该模型可以准确地预测PA的输入功率水平下，是从那些下，它被提取不同的行为。
A new, dynamic behavioral modeling technique, based on a time-delay support vector regression (SVR) method, is presented in this paper. As an advanced machine learning algorithm, the SVR method provides an effective option for behavioral modeling of radio frequency (RF) power amplifiers (PAs), taking into account the effects of both device nonlinearity and memory. The basic theory of the proposed modeling technique is given, along with a detailed model extraction procedure. Unlike traditional artificial neural network (ANN) techniques, which take time to determine the best configuration of the model, the SVR method can obtain the optimal model in short time, using the grid-search technique. An example of an optimal SVR model selection applied to an RF PA is also given; the performance of the selected model presents a big improvement when compared with the default SVR model. Experimental validation is performed using an LDMOS PA, a single device gallium nitride (GaN) PA, and a Doherty GaN PA, revealing that the new modeling methodology provides very efficient and extremely accurate prediction. Compared with traditional Volterra models, canonical piecewise linear models, and ANN-based models, the proposed SVR model gives improved performance with reasonable complexity. In addition, it is shown that the model can predict accurately the behavior of the PA under input power levels that are different from those under which it is extracted.