Behavioral-level modeling of GaN HEMT small-signal intrinsic noise based on DE-SVR algorithm

• DOI: 10.1016/j.mejo.2022.105426
• Publication Date: 2022-03-26T13:29:22Z
• Authors: Shaowei Wang; Jincan Zhang; Shi Yang; Na Li; Jinchan Wang; Min Liu
• Keywords: SIGNAL (programming language)

The Differential Evolution-Support Vector Regression (DE-SVR) algorithm is designed to model the small-signal intrinsic noise behavior of GaN HEMT. It not only overcomes local minimization shortcoming Back Propagation (BP) algorithm, but also uses DE (Differential Evolution) obtain best parameter c (punishment factor) and g (variance kernel function) Support (SVR) algorithm. In order validate superiority DE-SVR experiment compares modeling effects BP SVR in experimental results show that there are obvious advantages for characteristics