.png){kind=icon}
返回
Parallel Attention-Based Transformer for Channel Estimation in RIS-Aided 6G Wireless Communications
.png){kind=icon}
PRE
AI
DOI：10.1109/TVT.2024.3425433.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Accurate and fast channel estimation is one of the challenging problems in achieving practical reconfigurable intelligent surface (RIS)-aided wireless communication. However, a RIS-assisted communication system typically involves cascaded channels with intricate large-scale data distribution. Hence, practical implementation of the optimal minimum mean square error (MMSE) estimator may be infeasible due to its excessive complexity. In addition, most of the existing artificial intelligence (AI)-based channel estimation methods generally rely on convolutional neural networks, which only guarantee the estimation accuracy without considering the estimation time. To address these problems, an efficient parallel Transformer (EPformer) is proposed to achieve efficient channel estimation by jointly considering both estimation accuracy and estimation time. Firstly, the channel estimation problem is formulated as a parallel super-resolution (PSR) problem, given that the elements on the RIS are typically distributed in a two-dimensional manner. Then, the multi-head attention mechanism is employed to extract the deep channel features from the input data in parallel. To further enhance the estimation accuracy, the super-resolution block (SRB) is designed to denoise the noisy channel matrices. Finally, the encoder-to-decoder paradigm is developed to enhance the estimation performance. Extensive simulation results are provided to demonstrate the superiority of the proposed channel estimation scheme.
Keyword:
Channel estimation
Estimation
Communication systems
Accuracy
Wireless communication
Transformers
Superresolution
6G
artificial intelligence
attention mechanism
channel estimation
reconfigurable intelligent surface (RIS)
期刊
IF:
7.1
论文数:
1.8W
被引数:
6.6W
机构
引用论文
.png){kind=icon}
Joint Channel Estimation and Robust Beamforming Design for AF Relaying Using IMM Kalman Filters
PREAI
分享收藏Intelligent Reflecting Surface Enhanced Wireless Communications With Deep-Learning-Based Channel Prediction基于深度学习的信道预测智能反射面增强无线通信
PREAI
分享收藏
Smart Radio Environments Empowered by Reconfigurable Intelligent Surfaces: How It Works, State of Research, and The Road Ahead由可重构智能表面支持的智能无线电环境: 工作原理、研究现状和未来之路
OAAI
OAAI分享收藏Reconfigurable Intelligent Surfaces for Energy Efficiency in Wireless Communication无线通信能效的可重构智能表面OAAI
OAAI分享收藏Joint Transceiver Beamforming and Reflecting Design for Active RIS-Aided ISAC Systems有源RIS辅助ISAC系统的收发波束成形和反射联合设计
PREAI
分享收藏
查看更多内容