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
来源
ICC 2023-IEEE INTERNATIONAL CONFERENCE ON COMMUNICATIONS | 2023年
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] 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
  • [2] Continual Learning-Based Channel Estimation for 5G Millimeter-Wave Systems
    Kumar, Swaraj
    Vankayala, Satya Kumar
    Sahoo, Biswapratap Singh
    Yoon, Seungil
    2021 IEEE 18TH ANNUAL CONSUMER COMMUNICATIONS & NETWORKING CONFERENCE (CCNC), 2021,
  • [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] Deep learning-based massive MIMO channel estimation with reduced feedback
    Sadeghi, Nasser
    Azghani, Masoumeh
    DIGITAL SIGNAL PROCESSING, 2023, 137
  • [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 Frequency-Selective Channel Estimation for Hybrid mmWave MIMO Systems
    Abdallah, Asmaa
    Celik, Abdulkadir
    Mansour, Mohammad M.
    Eltawil, Ahmed M.
    IEEE TRANSACTIONS ON WIRELESS COMMUNICATIONS, 2022, 21 (06) : 3804 - 3821
  • [7] Deep Learning-Based Channel Estimation for Massive MIMO Systems with Pilot Contamination
    Hirose H.
    Ohtsuki T.
    Gui G.
    IEEE Open Journal of Vehicular Technology, 2021, 2 : 67 - 77
  • [8] 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
  • [9] 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
  • [10] Deep Learning-Based Channel Estimation to Mitigate Channel Aging in Massive MIMO With Pilot Contamination
    Hirose, Hiroki
    Yang, Siyuan
    Ohtsuki, Tomoaki
    Bouazizi, Mondher
    IEEE ACCESS, 2025, 13 : 1834 - 1845