The Dynamic Behavioral Model of RF Power Amplifiers With the Modified ANFIS

The adaptive neuro-fuzzy inference system (ANFIS) has been widely used for modeling different kinds of nonlinear systems including RF power amplifiers (PAs). The modified ANFIS (MANFIS) architecture is simpler than that of ANFIS, but with nearly the same performance for modeling nonlinear systems. I...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on microwave theory and techniques 2009-01, Vol.57 (1), p.27-35
Main Authors: Jianfeng Zhai, Jianfeng Zhai, Jianyi Zhou, Jianyi Zhou, Lei Zhang, Lei Zhang, Jianing Zhao, Jianing Zhao, Wei Hong, Wei Hong
Format: Article
Language:English
Subjects:
Adaptive neuro-fuzzy inference system (ANFIS)
Adaptive systems
adjacent channel leakage ratio (ACLR)
Amplifiers
Applied sciences
Channels
Circuit properties
Computational modeling
Computer simulation
digital predistortion (DPD)
Dynamical systems
Electric, optical and optoelectronic circuits
Electronic circuits
Electronic equipment and fabrication. Passive components, printed wiring boards, connectics
Electronics
Exact sciences and technology
Frequency domain analysis
Inference
Neural networks
Nonlinear dynamical systems
Nonlinear dynamics
Nonlinear systems
Power amplifiers
power amplifiers (PAs)
Power system modeling
Radio frequencies
Radio frequency
Radiofrequency amplifiers
Studies
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The adaptive neuro-fuzzy inference system (ANFIS) has been widely used for modeling different kinds of nonlinear systems including RF power amplifiers (PAs). The modified ANFIS (MANFIS) architecture is simpler than that of ANFIS, but with nearly the same performance for modeling nonlinear systems. In this paper, the MANFIS is applied to model RF PAs with memory effects. The simulation and experimental results both in the time and frequency domains show that this model has good modeling accuracy and the characteristics of faster convergence and lower computational complexity compared with the ANFIS model. The normalized mean squared errors of the MANFIS model are slightly lower than those of some other neural network models such as the real-valued time delay neural network, radial basis-function neural network, etc. Finally, the MANFIS model is successfully used in a digital predistortion system, which can provide over 10- dB adjacent channel leakage ratio improvement for three-carrier wideband code division multiple access signals.
ISSN:0018-9480
1557-9670
DOI:10.1109/TMTT.2008.2009085