Abstract
The deficiency of predistortion performance exists in indirect NN (Neural Network)-predistorter learning methods for nonlinear high power amplifiers (HPAs), and direct NN-predistorter learning methods possess great computational complexity. To circumvent these problems, in this paper we propose a novel NN-predistorter learning method with its structure developed by using some properties of nonlinear operators and its corresponding algorithm derived by using an approximation formula. The proposed method is based on the identification of NN post-distorter of the HPA, and then directly implements the efficient Levenberg-Marquardt back propagation algorithm. Thus, compared with the direct NN-predistorter learning method, our proposed method reduces the computational complexity and still keeps slightly better predistortion performance. Theoretical analysis and simulation results also show our proposed method outperforms the indirect NN-predistorter learning method in the term of about 5 dB adjacent channel power ratio improvement.
Similar content being viewed by others
References
Zou W., Wu Y. (1995) COFDM: An overview. IEEE Transactions on Broadcasting 41: 1–8
Huang D., Leung H., Huang X. (2006) Experimental evaluation of predistortion techniques for high-power amplifier. IEEE Transactions on Instrumentation and Measurement 55: 2155–2163
Bo A., Zhang-Dui Z., Gang Z., Yan Y., Rong-Tao X. (2008) A novel scheme for power amplifier predistortion based on indirect learning architecture. Wireless Personal Communications 46: 523–530. doi:10.1007/s11277-008-9451-z
Eun C., Powers E. J. (1997) A new Volterra predistorter based on the indirect learning architechtrue. IEEE Transactions on Signal Processing 45: 223–227
Yang, J., Gao, J., & Jiang, F. (2008). Neural network predistortion technique for nonlinear RF amplifiers. In Proceedings of the international conference on computer science and software engineering, pp. 769–772.
Luongvinh D., Kwon Y. (2006) A fully recurrent neural network-based model for predicting spectral regrowth of 3G handset power amplifiers with memory effects. IEEE Microwave and Wireless Components Letters 16: 621–623
Qian, Y., & Liu, F. (2006). Neural network predistortion technique for nonlinear power amplifiers with memory. In Proceedings of the 1st international conference on communications and networking, pp. 1–5.
Haykin S. (1999) Neural networks: A comprehensive foundation, 2nd edn. Prentice-Hall, New Jersey
Ding L., Zhou G. T., Morgan D. R., Ma Z., Kenney J. S., Kim J., Giardina C. R. (2002) Memory polynomial predistorter based on the indirect learning architecture. IEEE Globe Communications 1: 967–971
Morgan, D. R., Ma, Z., & Ding, L. (2003). Reducing measurement noise effects in digital predistortion of RF power amplifiers. In Proceedings of IEEE international conference on communications, 4, 2436–2439.
Mathews V. J., Sicuranza G. L. (2000) Polynomial signal processing (Wiley series in telecommunications and signal processing). John Wiley & Sons, New York
Lim Y. H., Cho Y. S., Cha I. W., Youn D. H. (1998) Adaptive nonlinear prefilter for compensation of distortion in nonlinear systems. IEEE Transactions on Signal Processing 46: 1726–1730
Qian Y., Yao T. (2002) Structure for adaptive predistortion suitable for efficient daptive algorithm application. Electronics Letters 38: 1282–1283
Zhou D., DeBrunner V. E. (2007) Novel adaptive nonlinear predistorters based on the direct learning algorithm. IEEE Transactions on Signal Processing 55: 120–133
Hagan M. T., Menhaj M. B. (1994) Training feedforward networks with the Marquardt algorithm. IEEE Transactions on Neural Networks 5: 989–993
Saleh A. (1981) Frequency-independent and frequency-dependent nonlinear models of TWT amplifiers. IEEE Transactions on Communications 29: 1715–1720
Kang H. W., Cho Y. S., Youn D. H. (1999) On compensating nonlinear distortions of an OFDM system using an efficient adaptive prdistorter. IEEE Transactions on Communications 47: 522–526
Lee B. M., De Figueiredo Rui J. P. (2006) Adaptive predistorter for linearization of high-power amplifiers in OFDM wireless communications. Circuits System, Signal Processing 25: 59–80
Ibnkahla M. (2000) Neural network predistortion technique for digital satellite communications. IEEE international conference on Acoustics, speech and signal processing, 6: 3506–3509
Li, J., & Iiow, J. (2005). A least-squares Volterra predistorter for compensation of non-linear effects with memory in OFDM transmitters. In Proceedings of the 3rd conference on annual communication networks and services research, pp. 197–202.
Author information
Authors and Affiliations
Corresponding author
Additional information
The Project was supported by the National Innovation Fund (No. 06026225101735) and National Nature Science Foundation of China (No. 60901004) and Special Fund for Basic Scientific Research of Central Colleges of China for Chang’an University (CHD2009JC098) and Special Fund for Basic Research support programs of Chang’an University and Shaanxi Engineering and Technique Research Center for Road and Traffic Detection.
Rights and permissions
About this article
Cite this article
Cui, H., Zhao, XM. A Novel NN-Predistorter Learning Method for Nonlinear HPA. Wireless Pers Commun 63, 469–482 (2012). https://doi.org/10.1007/s11277-010-0144-z
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11277-010-0144-z