Support Vector Regression-Based Behavioral Modeling Technique for RF Power Transistors

• Published in: IEEE microwave and wireless components letters Vol. 28; no. 5; pp. 428 - 430
• Main Authors: Cai, Jialin, King, Justin, Yu, Chao, Liu, Jun, Sun, Lingling
• Format: Journal Article
• Language: English
• Published: IEEE 01.05.2018
• Subjects: Computational modeling; Harmonic analysis; Integrated circuit modeling; Load modeling; Machine learning; nonlinear behavioral model; Predictive models; Radio frequency; support vector regression (SVR); Transistors
• ISSN: 1531-1309; 1558-1764
• DOI: 10.1109/LMWC.2018.2819427

A nonlinear behavioral modeling technique, based on support vector regression (SVR), is presented in this letter. As an advanced machine-learning technique, the SVR method provides a more effective way to determine the optimal model when compared with the more traditional modeling approaches based on artificial neural network (ANN) techniques. The proposed technique can overcome the well-known overfitting issue often associated with ANNs. In this letter, the basic theory of the proposed SVR modeling method is provided, along with details on model implementation in the context of RF transistor devices. Both simulation and experimental test examples for a 10-W gallium nitride (GaN) transistor are provided, revealing that the new modeling methodology provides a more efficient and robust prediction throughout the Smith chart when compared with ANNs, with the latest results showing excellent model fidelity at both the fundamental and at the second harmonic.