Continual Learning-Based MIMO Channel Estimation: A Benchmarking Study

被引:1
|
作者
Akrout, Mohamed [1 ]
Feriani, Amal [1 ]
Bellili, Faouzi [1 ]
Mezghani, Amine [1 ]
Hossain, Ekram [1 ]
机构
[1] Univ Manitoba, Dept Elect & Comp Engn, Winnipeg, MB, Canada
基金
加拿大自然科学与工程研究理事会;
关键词
Continual learning; task transferability; channel estimation; MIMO; Gauss-Markov channel model;
D O I
10.1109/ICC45041.2023.10278623
中图分类号
TN [电子技术、通信技术];
学科分类号
0809 ;
摘要
With the proliferation of deep learning techniques for wireless communication, several works have adopted learning-based approaches to solve the channel estimation problem. While these methods are usually promoted for their computational efficiency at inference time, their use is restricted to specific stationary training settings in terms of communication system parameters, e.g., signal-to-noise ratio (SNR) and coherence time. Therefore, the performance of these learning-based solutions will degrade when the models are tested on different settings than the ones used for training. This motivates our work in which we investigate continual supervised learning (CL) to mitigate the shortcomings of the current approaches. In particular, we design a set of channel estimation tasks wherein we vary different parameters of the channel model. We focus on Gauss-Markov Rayleigh fading channel estimation to assess the impact of non-stationarity on performance in terms of the mean square error (MSE) criterion. We study a selection of state-of-the-art CL methods and we showcase empirically the importance of catastrophic forgetting in continuously evolving channel settings. Our results demonstrate that the CL algorithms can improve the interference performance in two channel estimation tasks governed by changes in the SNR level and coherence time.
引用
收藏
页码:2631 / 2636
页数:6
相关论文
共 50 条
  • [1] Machine Learning-Based Channel Estimation in Massive MIMO with Channel Aging
    Yuan, Jide
    Hien Quoc Ngo
    Matthaiou, Michail
    2019 IEEE 20TH INTERNATIONAL WORKSHOP ON SIGNAL PROCESSING ADVANCES IN WIRELESS COMMUNICATIONS (SPAWC 2019), 2019,
  • [2] Deep Learning-Based Channel Estimation for Massive MIMO Systems
    Chun, Chang-Jae
    Kang, Jae-Mo
    Kim, Il-Min
    IEEE WIRELESS COMMUNICATIONS LETTERS, 2019, 8 (04) : 1228 - 1231
  • [3] Deep learning-based channel estimation in MIMO system for pilot decontamination
    Reddy, Gondhi Navabharat
    Kumar, C. V. Ravi
    INTERNATIONAL JOURNAL OF AD HOC AND UBIQUITOUS COMPUTING, 2023, 44 (03) : 148 - 166
  • [4] Online Deep Learning-Based Channel Estimation for Massive MIMO Systems
    Zhen, Xuanyu
    Lau, Vincent
    IEEE INTERNATIONAL CONFERENCE ON COMMUNICATIONS (ICC 2021), 2021,
  • [5] Deep Learning-Based Channel Estimation for Massive MIMO With Hybrid Transceivers
    Gao, Jiabao
    Zhong, Caijun
    Li, Geoffrey Ye
    Zhang, Zhaoyang
    IEEE TRANSACTIONS ON WIRELESS COMMUNICATIONS, 2022, 21 (07) : 5162 - 5174
  • [6] Deep learning-based massive MIMO channel estimation with reduced feedback
    Sadeghi, Nasser
    Azghani, Masoumeh
    DIGITAL SIGNAL PROCESSING, 2023, 137
  • [7] Deep Learning-Based Beamspace Channel Estimation in mmWave Massive MIMO Systems
    Zhang, Yinghui
    Mu, Yifan
    Liu, Yang
    Zhang, Tiankui
    Qian, Yi
    IEEE WIRELESS COMMUNICATIONS LETTERS, 2020, 9 (12) : 2212 - 2215
  • [8] Deep Learning-Based Channel Estimation for Beamspace mmWave Massive MIMO Systems
    He, Hengtao
    Wen, Chao-Kai
    Jin, Shi
    Li, Geoffrey Ye
    IEEE WIRELESS COMMUNICATIONS LETTERS, 2018, 7 (05) : 852 - 855
  • [9] Deep learning-based channel estimation for wireless ultraviolet MIMO communication systems
    Taifei Zhao
    Yuxin Sun
    Xinzhe Lü
    Shuang Zhang
    Optoelectronics Letters, 2024, 20 : 35 - 41
  • [10] Deep Learning-Based Downlink Channel Estimation for FDD Massive MIMO Systems
    Xiang, Bingtong
    Hu, Die
    Wu, Jun
    IEEE WIRELESS COMMUNICATIONS LETTERS, 2023, 12 (04) : 699 - 702