Abstract
In this paper, a high-speed pipelined architecture of dynamic neural network is proposed for power amplifier behavioral modeling. This architecture is implemented on field programmable gate array (FPGA) using Xilinx system generator and Virtex-6 FPGA ML605 Evaluation Kit. The novelty of the proposed architecture is that it provides higher operating frequency, lower output latency, and less required resources. These improvements are obtained by reducing the bit-width data and by efficiently redistributing the inserted pipelining delays. The new pipelined architecture is evaluated and compared to the conventional and pseudo-conventional ones in terms of the resource utilization, the maximum operating frequency, and the modeling performances using the 16-QAM modeled test signal. This architecture is verified using JTAG hardware co-simulation both for single step and free-running clock modes.
Similar content being viewed by others
References
Liu, T., Boumaiza, S., Ghannouchi, F. M. (2004). Dynamic behavioral modeling of 3G power amplifiers using real-valued time-delay neural networks. IEEE Transactions on Microwave Theory and Techniques, 52(3), 1025–1033.
Hwangbo, H., Jung, S. C., Yang, Y., Park, C. S., Kim, B. S., Nah, W. (2006). Power amplifier linearization using an indirect-learning-based inverse TDNN model. Microwave Journal, 49(11), 76–88.
Cao, Y., Chen, X., Wang, G. (2009). Dynamic behavioral modeling of nonlinear microwave devices using real-time recurrent neural network. IEEE Transactions on Electron Devices, 56(5), 1020–1026.
Rawat, M., Rawat, K., Ghannouchi, F. M. (2010). Adaptive digital predistortion of wireless power amplifiers/transmitters using dynamic real-valued focused time-delay line neural networks. IEEE Transactions on Microwave Theory and Techniques, 58(1), 95–104.
Mkadem, F., Boumaiza, S. (2011). Physically inspired neural network model for RF power amplifier behavioral modeling and digital predistortion. IEEE Transactions on Microwave Theory and Techniques, 59(4), 913–923.
Hui, M., Liu, T., Ye, Y., Zhang, H., Shen, D., Li, L. (2012). Dynamic behavioral modeling for strongly nonlinear Doherty PAs using real-valued time-delay recurrent RBF model. Journal of Electronics (China) ,29(1–2), 39–45.
Bahoura, M., Park, C.-W. (2012). FPGA-implementation of dynamic time delay neural network for power amplifier behavioral modeling. Analog Integrated Circuits and Signal Processing, 73(3), 819–828.
Ntouné, R. S. N., Bahoura, M., Park, C.-W. (2012). FPGA-implementation of pipelined neural network for power amplifier modeling. In:The 10th IEEE International NEWCAS Conference, Montréal, Canada (pp. 109–112).
Dias, F. M., Antunes, A., Mota, A. M. (2004). Artificial neural networks: A review of commercial hardware. Engineering Applications of Artificial Intelligence, 17(8), 945–952.
Misra, J., Saha, I. (2010). Artificial neural networks in hardware: A survey of two decades of progress. Neurocomputing ,74, 239–255.
Gironés, R. G., Palero, R. C., Boluda, J. C., Cortés, A. S. (2005). FPGA implementation of a pipelined on-line backpropagation. Journal of VLSI Signal Processing Systems, 40, 189–213.
Ortigosa, E. M., Cañas, A., Ros, E., Ortigosa, P. M., Mota, S., Díaz, J. (2006). Hardware description of multi-layer perceptrons with different abstraction levels. Microprocessors and Microsystems, 30(7), 435–444.
Armato, A., Fanucci, L., Scilingo, E., Rossi, D. D. (2011). Low-error digital hardware implementation of artificial neuron activation functions and their derivative. Microprocessors and Microsystems, 35(6), 557–567.
Gilabert, P., Cesari, A., Montoro, G., Bertran, E., Dilhac, J.-M. (2008). Multi-lookup table FPGA implementation of an adaptive digital predistorter for linearizing RF power amplifiers with memory effects. IEEE Transactions on Microwave Theory and Techniques, 56(2), 372–384.
Kwan, A., Ghannouchi, F., Hammi, O., Helaoui, M., Smith, M. (2012). Look-up table-based digital predistorter implementation for field programmable gate arrays using long-term evolution signals with 60 MHz bandwidth. Science, Measurement Technology, IET, 6(3), 181–188.
Gilabert, P. L., Montoro, G. (2013). Computationally efficient real-time digital predistortion architectures for envelope tracking power amplifiers. International Journal of Microwave and Wireless Technologies, 5, 187–193.
Ku, H., Kenney, J. S. (2003). Behavioral modeling of nonlinear RF power amplifiers considering memory effects. IEEE Transactions on Microwave Theory and Techniques, 51(12), 2495–2504.
Ding, L., Zhou, G. T., Morgan, D. R., Ma, Z., Kenney, J. S., Kim, J., Giardina, C. R. (2004). A robust digital baseband predistorter constructed using memory polynomials. IEEE Transactions on Communications, 52(1), 159–165.
Mrabet, N., Mohammad, I., Mkadem, F., Rebai, C., Boumaiza, S. (2012). Optimized hardware for polynomial digital predistortion system implementation. In: 2012 IEEE Topical Conference on Power Amplifiers for Wireless and Radio Applications (PAWR).
Guan, L., Zhu, A. (2010). Low-cost FPGA implementation of Volterra series-based digital Predistorter for RF power amplifiers. IEEE Transactions on Microwave Theory and Techniques, 58(4), 866–872.
Zhu, A., Pedro, J., Brazil, T. (2006). Dynamic deviation reduction-based Volterra behavioral modeling of RF power amplifiers. IEEE Transactions on Microwave Theory and Techniques, 54(12), 4323–4332.
Liszewski, J., Schubert, B., Keusgen, W., Kortke, A. (2011). Low-complexity FPGA implementation of Volterra predistorters for power amplifiers. In: The IEEE Topical Conference on Power Amplifiers for Wireless and Radio Applications (PAWR) (pp. 41–44).
Jiménez, V., Jabrane, Y., Armada, A., Said, B., Ouahman, A. (2011). High power amplifier pre-distorter based on neural-fuzzy systems for OFDM signals. IEEE Transactions on Broadcasting, 57(1), 149–158.
Kwan, A., Helaoui, M., Boumaiza, S., Smith, M., Ghannouchi, F. (2009). Wireless communications transmitter performance enhancement using advanced signal processing algorithms running in a hybrid DSP/FPGA platform. Journal of Signal Processing Systems, 56(2–3), 187–198.
Haykin, S. (1999). Neural networks: A comprehensive foundation (2nd ed.). Upper Saddle River: Prentice-Hall.
Bahoura, M., Ezzaidi, H. (2011). FPGA-implementation of parallel and sequential architectures for adaptive noise cancelation. Circuits, Systems, and Signal Processing, 30(6), 1521–1548.
Bahoura, M., Park, C.-W. (2011). FPGA-implementation of high-speed MLP neural network. In: The 18th IEEE International Conference on Electronics, Circuits, and Systems (ICECS), Beirut, Lebanon (pp. 426–429).
Bahoura, M., Ezzaidi, H. (2012). FPGA-implementation of discrete wavelet transform with application to signal denoising. Systems, and Signal Processing, 31(3), 987–1015.
Long, G., Ling, F., Proakis, J. (1989). LMS algorithm with delayed coefficient adaptation. IEEE Transactions on Acoustics, Speech, and Signal Processing, 37(9), 1397–1405.
Saleh, A. A. M. (1981). Frequency-independent and frequency-dependent nonlinear models of TWT amplifiers. IEEE Transactions on communications, 29(11), 1715–1720.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Bahoura, M. FPGA implementation of high-speed neural network for power amplifier behavioral modeling. Analog Integr Circ Sig Process 79, 507–527 (2014). https://doi.org/10.1007/s10470-014-0263-7
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10470-014-0263-7