Skip to main content

Lund University Publications

LUND UNIVERSITY LIBRARIES

Machine Learning Based Digital Pre-Distortion in Massive MIMO Systems : Complexity-Performance Trade-offs

Sheikhi, Ashkan LU orcid and Edfors, Ove LU orcid (2023) 2023 IEEE Wireless Communications and Networking Conference, WCNC 2023 In IEEE Wireless Communications and Networking Conference, WCNC 2023-March.
Abstract

In this paper, we study the trade-off between complexity and performance in massive MIMO systems with neural-network based digital pre-distortion (NN-DPD) blocks at the base station. In particular, we consider a multi-user massive MIMO system with per-antenna NN-DPDs, each with an adjustable NN architecture in terms of the size and the number of NN hidden layers. We first analyze the system performance in terms of compensation of the non-linear hardware distortion for different levels of NN-DPD complexity and the number of antennas. We illustrate the required level of complexity in the trained NN-DPD blocks to approach the performance of an ideal conventional DPD. The statistics of the signal to interference and noise plus distortion... (More)

In this paper, we study the trade-off between complexity and performance in massive MIMO systems with neural-network based digital pre-distortion (NN-DPD) blocks at the base station. In particular, we consider a multi-user massive MIMO system with per-antenna NN-DPDs, each with an adjustable NN architecture in terms of the size and the number of NN hidden layers. We first analyze the system performance in terms of compensation of the non-linear hardware distortion for different levels of NN-DPD complexity and the number of antennas. We illustrate the required level of complexity in the trained NN-DPD blocks to approach the performance of an ideal conventional DPD. The statistics of the signal to interference and noise plus distortion ratio for a randomly located UE are selected as the performance metrics. We then assume a limited total digital computation power to be allocated among the NN-DPD blocks and propose to select the NN-DPD architecture of each TX branch based on the channel conditions of its corresponding antenna. To illustrate the importance of such a smart DPD resource allocation, we have analyzed the performance of a massive MIMO system with different NN-DPD architecture selection strategies. Numerical results indicate that by adopting the smart NN-DPD resource allocation, a significant boost in the system performance can be achieved, making room for reducing the overall system cost when scaling a massive MIMO system.

(Less)
Please use this url to cite or link to this publication:
author
and
organization
publishing date
type
Chapter in Book/Report/Conference proceeding
publication status
published
subject
keywords
Digital Predistortion, Machine Learning, Massive MIMO
host publication
2023 IEEE Wireless Communications and Networking Conference, WCNC 2023 - Proceedings
series title
IEEE Wireless Communications and Networking Conference, WCNC
volume
2023-March
publisher
IEEE - Institute of Electrical and Electronics Engineers Inc.
conference name
2023 IEEE Wireless Communications and Networking Conference, WCNC 2023
conference location
Glasgow, United Kingdom
conference dates
2023-03-26 - 2023-03-29
external identifiers
  • scopus:85159783118
ISSN
1525-3511
ISBN
9781665491228
DOI
10.1109/WCNC55385.2023.10118801
language
English
LU publication?
yes
id
320daf40-1a91-4171-83d3-d20b7e7d0e71
date added to LUP
2023-09-25 13:41:25
date last changed
2024-03-22 00:55:02
@inproceedings{320daf40-1a91-4171-83d3-d20b7e7d0e71,
  abstract     = {{<p>In this paper, we study the trade-off between complexity and performance in massive MIMO systems with neural-network based digital pre-distortion (NN-DPD) blocks at the base station. In particular, we consider a multi-user massive MIMO system with per-antenna NN-DPDs, each with an adjustable NN architecture in terms of the size and the number of NN hidden layers. We first analyze the system performance in terms of compensation of the non-linear hardware distortion for different levels of NN-DPD complexity and the number of antennas. We illustrate the required level of complexity in the trained NN-DPD blocks to approach the performance of an ideal conventional DPD. The statistics of the signal to interference and noise plus distortion ratio for a randomly located UE are selected as the performance metrics. We then assume a limited total digital computation power to be allocated among the NN-DPD blocks and propose to select the NN-DPD architecture of each TX branch based on the channel conditions of its corresponding antenna. To illustrate the importance of such a smart DPD resource allocation, we have analyzed the performance of a massive MIMO system with different NN-DPD architecture selection strategies. Numerical results indicate that by adopting the smart NN-DPD resource allocation, a significant boost in the system performance can be achieved, making room for reducing the overall system cost when scaling a massive MIMO system.</p>}},
  author       = {{Sheikhi, Ashkan and Edfors, Ove}},
  booktitle    = {{2023 IEEE Wireless Communications and Networking Conference, WCNC 2023 - Proceedings}},
  isbn         = {{9781665491228}},
  issn         = {{1525-3511}},
  keywords     = {{Digital Predistortion; Machine Learning; Massive MIMO}},
  language     = {{eng}},
  publisher    = {{IEEE - Institute of Electrical and Electronics Engineers Inc.}},
  series       = {{IEEE Wireless Communications and Networking Conference, WCNC}},
  title        = {{Machine Learning Based Digital Pre-Distortion in Massive MIMO Systems : Complexity-Performance Trade-offs}},
  url          = {{http://dx.doi.org/10.1109/WCNC55385.2023.10118801}},
  doi          = {{10.1109/WCNC55385.2023.10118801}},
  volume       = {{2023-March}},
  year         = {{2023}},
}