Attention Guided Multi-task Network for Joint CFO and Channel Estimation in OFDM Systems

The existence of high carrier frequency offset (CFO) and fading channels degrades the performance of communication systems in high mobility environments significantly. To address these challenges, in this paper, we propose an attention guided multi-task network for joint CFO and channel estimation i...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on wireless communications 2024-01, Vol.23 (1), p.1-1
Main Authors: Chen, Zhuo, Liu, Zhiang, Geng, Xue, Zhao, Yingxin, Wu, Hong
Format: Article
Language:English
Subjects:
attention mechanism
Carrier frequencies
carrier frequency offset (CFO) estimation
Channel estimation
Communications systems
Estimation
Frequency synchronization
joint
multi-task learning
Multitasking
Neural networks
OFDM
Orthogonal Frequency Division Multiplexing
Performance degradation
Task analysis
Wireless communication
Citations: Items that this one cites
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The existence of high carrier frequency offset (CFO) and fading channels degrades the performance of communication systems in high mobility environments significantly. To address these challenges, in this paper, we propose an attention guided multi-task network for joint CFO and channel estimation in orthogonal frequency division multiplexing (OFDM) systems. Specifically, considering the correlation between CFO estimation and channel estimation, we construct a multi-task neural network framework which consists of a shared branch (SB), a CFO estimation branch (CFOEB) and a channel estimation branch (CEB). Among them, the SB extracts common features of two tasks, and the CFOEB and CEB make more detailed CFO and channel estimation, respectively. To further suppress the influence of CFO estimation error on channel estimation, we introduce an attention guided module (AGM) which completes the re-calibration of the channel dimension on the basis of different CFO characteristics. We train the whole network by an end-to-end paradigm and construct a suitable multi-task loss function to balance the losses between different tasks. Simulation results demonstrate that the proposed attention guided multi-task learning based joint CFO and channel estimation scheme outperforms the conventional methods and has greater robustness under various conditions.
ISSN:1536-1276
1558-2248
DOI:10.1109/TWC.2023.3277561