期刊
IEEE TRANSACTIONS ON COMMUNICATIONS
卷 69, 期 7, 页码 4937-4952出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TCOMM.2021.3072726
关键词
Channel estimation; super-resolution; deep learning; non-stationary
资金
- National Natural Science Foundation of China (NSFC) [62071284, 61871262, 61901251, 61904101]
- National Key Research and Development Program of China [2017YEF0121400, 2019YFE0196600]
- Innovation Program of Shanghai Municipal Science and Technology Commission [20JC1416400]
- Pudong New Area Science and Technology Development Fund
- Shanghai Institute for Advanced Communication and Data Science (SICS)
By utilizing super-resolution image recovery scheme and recurrent network structure, a novel channel estimation scheme has been developed, which outperforms conventional methods in both stationary and non-stationary environments.
Y Channel estimation is crucial to modern wireless systems and becomes more and more challenging with the growth of user throughput in sub-6 GHz multiple input multiple output configuration. Plenty of literature spends great efforts in improving the estimation accuracy, while the interpolation schemes are overlooked. To deal with this challenge, we exploit the super-resolution image recovery scheme to model the non-linear interpolation mechanisms. Moreover, in order to extend the estimation scheme into the non-stationary environment which is especially attractive in the coming 6G, we utilize the recurrent network structure to approximate the non-linear channel statistic correlation to model the non-stationary behavior which is difficult to accomplish in the theoretical way. To make it more practical, we offline generate numerical channel coefficients according to the statistical channel models to train the neural networks and directly apply them in different environments. As shown in this paper, the proposed unified super-resolution based channel estimation scheme can outperform the conventional approaches in both stationary and non-stationary scenarios, which we believe can significantly change the current channel estimation method in the near future.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据