An adaptive fuzzy logic system for the compensation of nonlinear distortion in wireless power amplifiers

• Published in: Neural computing & applications Vol. 30; no. 8; pp. 2539 - 2554
• Main Authors: Vaskovic, Mina, Kodogiannis, Vassilis S., Budimir, Djuradj
• Format: Journal Article
• Language: English
• Published: London Springer London 01-10-2018; Springer Nature B.V
• Subjects: Adaptive systems; Artificial Intelligence; Comparative studies; Computational Biology/Bioinformatics; Computational Science and Engineering; Computer Science; Data Mining and Knowledge Discovery; Distortion; Fuzzy logic; Fuzzy systems; Image Processing and Computer Vision; Inverse dynamics; Neural networks; Original Article; Power amplifiers; Probability and Statistics in Computer Science; Pre-distortion; RF power amplifiers; Neuro-fuzzy systems; Neural networks; Linearization
• ISSN: 0941-0643; 1433-3058
• DOI: 10.1007/s00521-017-2849-3

Computational intelligent systems are becoming an increasingly attractive solution for power amplifier (PA) behavioural modelling, due to their excellent approximation capability. This paper utilizes an adaptive fuzzy logic system (AFLS) for the modelling of the highly nonlinear MIMIX CFH2162-P3 PA. Moreover, PA’s inverse model based also on AFLS has been developed in order to act as a pre-distorter unit. Driving an LTE 1.4 MHz 64 QAM signal at 880 MHz as centre frequency at PA’s input, very good modelling performance was achieved, for both PA’s forward and inverse dynamics. A comparative study of AFLS and neural networks (NN) has been carried out to establish AFLS as an effective, robust and easy-to-implement baseband model, which is suitable for inverse modelling of PAs and capable to be used as an effective digital pre-distorter. Pre-distortion system based on AFLS achieved distortion suppression of 84.2%, compared to the 48.4% gained using the NN-based equivalent scheme.