Comparative analysis of nonlinear behavioral models for GaN HEMTs based on machine learning techniques

A variety of novel behavioral modeling techniques have been reported to accurately capture the nonlinear characteristics of GaN devices. For the purpose of describing GaN HEMT large-signal behavior, machine learning-based approaches have been proposed. There is, however, a lack of comparison and analysis of their performance with different machine learning techniques in these studies. An examination of machine learning-based large-signal modeling techniques is presented in this article. To develop large-signal models of GaN HEMT, a range of commonly used modeling techniques such as artificial neural networks (ANN), random sample consistency (RANSAC), support vector regression (SVR), Gaussian process regression (GPR), decision trees (DTs), and genetic algorithm-assisted ANN (GA-ANN) are described and employed. Afterwards, integrated modeling techniques such as Bootstrap aggregation (BA), random forests (RF), AdaBoost, and gradient tree boosting (GTB) are reviewed and tested for their capabilities in developing GaN HEMT LSM. The hyperparameters of each built model are modified using the random search optimization (RSO) method, and five-fold cross-validation is used during validation. In order to identify optimal algorithms for nonlinear behavioral modeling of GaN devices, the model prediction results are comprehensively analyzed.