skip to main content

Explore Research Products in the NSF-PAR

Title: Virtual DPD Neural Network Predistortion for OFDM-based MU-Massive MIMO
The nonlinearities of power amplifiers in massive MIMO arrays introduce unwanted spectral regrowth, which is typically avoided via digital predistortion at each amplifier. However, as the number of base station antennas scales up, so does the computational burden of per-antenna linearization. This work introduces a neural-network virtual digital predistortion (vDPD) scheme that operates before the linear precoder for OFDM-based massive MU-MIMO systems. By applying predistortion before the precoder, complexity scales primarily with the number of users. We can achieve comparable linearization along the user beams by training our neural network based on the memory polynomial, predistortion-per-antenna approach. We verify our algorithm through an exhaustive simulator that includes high-order amplifier nonlinearities, memory effects, and variance across the amplifier models.  more » « less
Award ID(s):
2016727
NSF-PAR ID:
10357918
Author(s) / Creator(s):
; ; ;
Date Published:
Journal Name:
2021 55th Asilomar Conference on Signals, Systems, and Computers
Page Range / eLocation ID:
376 to 380
Format(s):
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. ; ; ( , 2019 IEEE International Workshop on Signal Processing Systems (SiPS))
    null (Ed.)
    Digital predistortion is the process of using digital signal processing to correct nonlinearities caused by the analog RF front-end of a wireless transmitter. These nonlinearities contribute to adjacent channel leakage, degrade the error vector magnitude of transmitted signals, and often force the transmitter to reduce its transmission power into a more linear but less power-efficient region of the device. Most predistortion techniques are based on polynomial models with an indirect learning architecture which have been shown to be overly sensitive to noise. In this work, we use neural network based predistortion with a novel neural network training method that avoids the indirect learning architecture and that shows significant improvements in both the adjacent channel leakage ratio and error vector magnitude. Moreover, we show that, by using a neural network based predistorter, we are able to achieve a 42% reduction in latency and 9.6% increase in throughput on an FPGA accelerator with 15% fewer multiplications per sample when compared to a similarly performing memory-polynomial implementation. 
    more » « less
  2. ; ; ( , 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP))
    Recently a number of nonlinear precoding algorithms have been developed for designing a downlink transmit signal that is constrained by some nonlinearity, such as one-bit quantization, power-amplifier saturation or constant modulus. These methods use iterative search algorithms to directly design the signal that is transmitted from each antenna. Since the dimension of the search space equals the number of antennas, the computational complexity of these approaches can be high for massive MIMO scenarios. Thus, in this paper we pose the problem in a smaller dimensional space by constraining the signal prior to the nonlinearity to be the output of a linear precoder. The search is then over the vector of predistorted symbols at the input to the linear precoder, which is typically much smaller than the number of antennas. We focus on algorithms that minimize the bit error rate at the receivers, and show that performance can be obtained that is similar to algorithms that operate directly in the antenna domain. 
    more » « less
  3. ; ; ; ( , IEEE Transactions on Information Theory)
    A promising approach to deal with the high hardware cost and energy consumption of massive MIMO transmitters is to use low-resolution digital-to-analog converters (DACs) at each antenna element. This leads to a transmission scheme where the transmitted signals are restricted to a finite set of voltage levels. This paper is concerned with the analysis and optimization of a low-cost quantized precoding strategy, referred to as linear-quantized precoding, for a downlink massive MIMO system under Rayleigh fading. In linear-quantized precoding, the signals are first processed by a linear precoding matrix and subsequently quantized component-wise by the DAC. In this paper, we analyze both the signal-to-interference-plus-noise ratio (SINR) and the symbol error probability (SEP) performances of such linear-quantized precoding schemes in an asymptotic framework where the number of transmit antennas and the number of users grow large with a fixed ratio. Our results provide a rigorous justification for the heuristic arguments based on the Bussgang decomposition that are commonly used in prior works. Based on the asymptotic analysis, we further derive the optimal precoder within a class of linear-quantized precoders that includes several popular precoders as special cases. Our numerical results demonstrate the excellent accuracy of the asymptotic analysis for finite systems and the optimality of the derived precoder. 
    more » « less
  4. ; ; ; ( , 2019 IEEE 53rd Asilomar Conference on Signals, Systems and Computers)
    null (Ed.)
    We demonstrate digital predistortion (DPD) using a novel, neural-network (NN) method to combat the nonlinearities in power amplifiers (PAs), which limit the power efficiency of mobile devices, increase the error vector magnitude, and cause inadequate spectral containment. DPD is commonly done with polynomial-based methods that use an indirect-learning architecture (ILA) which can be computationally intensive, especially for mobile devices, and overly sensitive to noise. Our approach using NNs avoids the problems associated with ILAs by first training a NN to model the PA then training a predistorter by backpropagating through the PA NN model. The NN DPD effectively learns the unique PA distortions, which may not easily fit a polynomial-based model, and hence may offer a favorable tradeoff between computation overhead and DPD performance. We demonstrate the performance of our NN method using two different power amplifier systems and investigate the complexity tradeoffs. 
    more » « less
  5. ; ; ; ; ( , IEEE International Conference on Communications)
    The primary source of nonlinear distortion in wireless transmitters is the power amplifier (PA). Conventional digital predistortion (DPD) schemes use high-order polynomials to accurately approximate and compensate for the nonlinearity of the PA. This is not practical for scaling to tens or hundreds of PAs in massive multiple-input multiple-output (MIMO) systems. There is more than one candidate precoding matrix in a massive MIMO system because of the excess degrees-of-freedom (DoFs), and each precoding matrix requires a different DPD polynomial order to compensate for the PA nonlinearity. This paper proposes a low-order DPD method achieved by exploiting massive DoFs of next-generation front ends. We propose a novel indirect learning structure which adapts the channel and PA distortion iteratively by cascading adaptive zero forcing precoding and DPD. Our solution uses a 3rd order polynomial to achieve the same performance as the conventional DPD using an 11th order polynomial for a 10010 massive MIMO configuration. Experimental results show a 70% reduction in computational complexity, enabling ultra-low latency communications. 
    more » « less
  • Citation Formats
  • MLA
  • APA
  • Chicago
  • BibTeX
  • Save / Share this Record
  • Send to Email