Abstract
In this paper, a novel mechanism is studied to improve the performance of the channel state information (CSI) feedback in massive multiple-input multiple-output (MIMO) systems. The proposed mechanism encompasses convolutional neural network (CNN)-based CSI compression and reconstruction structure. In this structure, the long-short term memory (LSTM) is adopted to learn temporal correlation of channels, and then, an attention mechanism is developed to perceive local information and automatically weight feature information. In addition, the CNN framework is further adjusted to reduce the number of training parameters and accelerate CSI recovery. The CNN structure with optimal training parameters can be achieved via offline iterative training and learning based on various training datasets. Comparative experimental studies demonstrate the effectiveness of the proposed approach that the trained CNN can obtain the higher feedback accuracy and better system performance in massive MIMO CSI online feedback reconstruction. Moreover, the proposed scheme in the less parameters-based neural network owns a higher performance with lower computational complexity compared to the conventional algorithms.
Highlights
Massive multiple-input multiple-output (MIMO) is regarded as one of the key technologies for the generation of wireless networks [1]
We propose a novel channel state information (CSI) feedback and recovery mechanism in the frequency division duplex (FDD) massive MIMO system called LSTMAttention CsiNet
THE SYSTEM MODEL Consider a FDD massive MIMO system, where the base station (BS) is equipped with Nt transmit antennas with uniform linear array (ULA) and the user equipment (UE) is equipped with one single antenna
Summary
Massive MIMO is regarded as one of the key technologies for the generation of wireless networks [1]. Some other researches, including least absolute shrinkage and selection operator (LASSO) 1-solver [11] and approximate message passing (AMP) [12], have been proposed to recover compressive CSI Such solutions are based on the sparse priors which could hardly be restored because the practical channel is approximately sparse. We propose a novel CSI feedback and recovery mechanism in the FDD massive MIMO system called LSTMAttention CsiNet. Compression and decompression modules of the mechanism employ a LSTM-Attention to enhance the performance of channel recovery, respectively. We propose a lightweight LSTM-Attention CsiNet by adjusting connection mode between the LSTM-Attention and FCN This lightweight network adopts FCN compress feature information to a lower vector and input to LSTMAttention, which effectively reduces the number of weights and biases from LSTM-Attention and accelerates the channel recovery
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
