A Generic and Efficient Globalized Kernel Mapping-Based Small-Signal Behavioral Modeling for GaN HEMT

Abstract

The work reported in this paper explores a novel Particle Swarm Optimization (PSO) tuned Support Vector Regression (SVR) based technique to develop the small-signal behavioral model for GaN High Electron Mobility Transistor (HEMT). The proposed technique investigates issues such as kernel selection and model optimization usually encountered in the application of SVR to model the GaN based HEMT devices. Here, the PSO algorithm is utilized to find the optimal hyperparameters to minimize the fitness function. To enumerate the efficiency and the generalization capability of the predictors, the performance of the model is investigated in terms of mean square error (MSE) and mean relative error (MRE). A very good agreement is found between the measured S-parameters and the proposed model for multi-biasing sets over the complete frequency range of 1 GHz-18 GHz. The proposed technique is even used to test the frequency extrapolation capability of the model. A comparative analysis indicates that the proposed PSO-SVR predictor achieves significantly improved computational efficiency and the overall prediction accuracy. To demonstrate the ready usefulness of the modeling approach, the developed model has been incorporated in CAD environment using MATLAB Cosimulation in ADS Ptolemy. Subsequently, the small-signal stability analysis is performed and gain of a power amplifier configuration designed using the proposed GaN HEMT model is determined.

Demonstration of CAD Deployability for GPR Based Small-Signal Modelling of GaN HEMT

“…Their models give better performance as compared to the traditional ANN based models. The alternative solution to address initialization and convergence issues in ANN based GaN HEMT modelling is by the use PSO-SVR in the model development of GaN HEMT [16], [17]. The SVR can drive the solutions towards global minimums because it has an inbuilt SRM principle as opposed to the traditional ANN based approaches.…”

“…This can therefore facilitate the easy implementation of the device models in circuit design tools and the PAs can be produced on mass-scale easily. Therefore, recently a number of papers have been reported to describe the smallsignal behavior of GaN HEMT using Artificial Neural Network [11]- [14], global optimization-oriented ANN [15] and Particle swarm optimization (PSO)-based Support Vector Regression (SVR) [16]- [17]. But due to parametric nature of ANN and SVR algorithms, the performance of developed models heavily depend upon the nature of the dataset.…”

Global Modeling of Millimeter-Wave Transistors: Analysis of Electromagnetic-Wave Propagation Effects

“…Using experimental results in modeling requires data fitting and de-embedding the influence of pad parasitics and interconnect line effects. Measurement-based models are studied in [6][7][8][9][10]. A comparison between three optimization techniques: Genetic Algorithm, Grey Wolf Optimization, and Harris-Hawks Optimization was studied in [6].…”

A reliable parameter extraction method for the augmented GaN high electron mobility transistor small‐signal model

“…In recent years, compound semiconductors have attracted more and more attention 1 . Compared with other materials, GaN materials have the advantages of high electron mobility and breakdown electric field, and large forbidden band width, 2,3 which make GaN high electron mobility transistors (HEMTs) widely used 4–6 . Therefore, an accurate GaN HEMT small‐signal equivalent model with its parameter extraction is very important for the application and development of GaN HEMT devices 7–11 …”