arXiv cs.AI· Dianxin Luan, John Thompson·· 10 小时前AI 评分24
通过设计训练数据实现抗多普勒效应的鲁棒信道估计神经网络
Achieving Robust Channel Estimation Neural Networks on Doppler effects by Designed Training Data
AI 导读
研究提出一套合成训练数据的设计准则，使离线训练的神经网络无需先验信息或在线训练即可在不同无线信道上精确估计信道，尤其适用于极高多普勒频移和不同多普勒频谱场景。仿真显示，不同复杂度的网络架构在未见过的功率延迟分布（PDP）和多普勒频移信道上均能保持稳定性能，泛化能力似乎与架构无关。
正文 · 原文
Abstract:Channel estimation is crucial in wireless communication systems. Many existing works train and test their models using the same or similar channel. However, practical channels are infinitely diverse and time-variant while data-driven algorithms often degrade on new and previously unseen channels. This prohibits the practical implementation of neural networks for channel estimation, particularly in high speed scenarios characterized by rapidly channel profile changes and very high Doppler shifts. Online training can fine-tune models to adapt to new channels, but requires high computation resource and incurs significant latency for physical-layer devices. Moreover, online training cannot exhaustively cover all possible channels because there are infinitely many possible channels. Therefore, we investigate the ability of neural networks to generalize to wireless channels. This paper proposes design criteria to generate synthetic training data, which guaranty that the resulting networks perform robustly across wireless channels, especially for very high Doppler shifts and different Doppler spectra. It ensures that offline-trained neural networks require no prior information or online training to precisely estimate the new channels. To demonstrate general applicability, we use neural networks with different levels of complexity to show that the generalization achieved appears to be independent of architecture. From simulation results, neural networks achieve a certain performance across wireless channels with different unseen power delay profiles (PDP) and Doppler shifts.
| Subjects: | Signal Processing (eess.SP); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2611.14267 [eess.SP] |
| (or arXiv:2611.14267v1 [eess.SP] for this version) | |
| https://doi.org/10.48550/arXiv.2611.14267 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Dianxin Luan [view email]
[v1]
Tue, 10 Nov 2026 16:11:11 UTC (420 KB)
来源：arXiv cs.AI · arxiv.org