Early stopping criteria for adaptive training of dynamic nonlinear behavioural models

As the physical makeup of cellular basestations evolve into systems with multiple parallel transmission paths the effort involved in modelling these complex systems increases considerably. One task in particular which contributes to signal distortion on each signal path, is the power amplifier. In power amplifier (PA) modelling, Recursive Least Squares (RLS) has been used in the past to train Volterra models with memory terms. The Volterra model is widely used for modelling of PAs. In this paper we present a comparison of the stability performance for a PA model during training for various model memory lengths, model orders of non linearity and signal sample rates. This examination provides a technique to avoid instability occurring during the adaptive training of dynamic nonlinear behavioural models.

[1]  Wei Xiang,et al.  Big data-driven optimization for mobile networks toward 5G , 2016, IEEE Network.

[2]  B. Farhang-Boroujeny,et al.  Adaptive Filters: Theory and Applications , 1999 .

[3]  V. J. Mathews,et al.  Polynomial Signal Processing , 2000 .

[4]  T.J. Brazil,et al.  Simplified Volterra Series Based Behavioral Modeling of RF Power Amplifiers Using Deviation-Reduction , 2006, 2006 IEEE MTT-S International Microwave Symposium Digest.

[5]  Benjamin Steinberg,et al.  Representation Theory of Finite Groups: An Introductory Approach , 2011 .

[6]  Andrew H. Jazwinski,et al.  Adaptive filtering , 1969, Autom..

[7]  Ronan Farrell,et al.  Estimation of Sparse Memory Taps for RF Power Amplifier Behavioral Models , 2015, IEEE Microwave and Wireless Components Letters.

[8]  Wei Hong,et al.  Behavioral Modeling of Power Amplifiers With Dynamic Fuzzy Neural Networks , 2010, IEEE Microwave and Wireless Components Letters.

[9]  Ronan Farrell,et al.  Selection of compressed training data for RF power amplifier behavioral modeling , 2015, 2015 10th European Microwave Integrated Circuits Conference (EuMIC).

[10]  G. Wittum,et al.  Adaptive filtering , 1997 .