A Novel CSI Feedback Approach for Massive MIMO Using LSTM-Attention CNN

Li, Qi; Zhang, Aihua; Liu, Pengcheng; Li, Jianjun; Li, Chunlei

doi:10.1109/access.2020.2963896

Cited by 15 publications

(9 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the case of channel training of a Time Division Duplex (TDD) system, a channel state information (CSI) parameter is used in the communication between the UE and the network in order to describe the channel quality and recommend a proper precoding matrix [12]. The CSI of the downlink channel is estimated by performing measurements on the uplink channel by using the transmitted pilots from the users [13].…”

Section: From Mu-mimo To Massive Mimomentioning

confidence: 99%

Massive MIMO Systems for 5G Communications

Khwandah

Cosmas

Lazaridis

et al. 2021

Wireless Pers Commun

View full text Add to dashboard Cite

Massive MIMO will improve the performance of future 5G systems in terms of data rate and spectral efficiency, while accommodating a large number of users. Furthermore, it allows for 3D beamforming in order to provide more degrees of freedom and increase the number of high-throughput users. Massive MIMO is expected to provide more advantages compared to other solutions in terms of energy and spectral efficiency. This will be achieved by focusing the radiation towards the direction of the intended users, thus implementing simultaneous transmission to many users while keeping interference low. It can boost the capacity compared to a conventional antenna solution, resulting in a spectral efficiency up to 50 times greater than that provided by actual 4G technology. However, to take full advantage of this technology and to overcome the challenges of implementation in a real environment, a complicated radio system is required. The purpose of this work is to present the MIMO technology evolution and challenges in a simple introductory way and investigate potential system enhancements.

show abstract

Section: From Mu-mimo To Massive Mimomentioning

confidence: 99%

Massive MIMO Systems for 5G Communications

Khwandah

Cosmas

Lazaridis

et al. 2021

Wireless Pers Commun

View full text Add to dashboard Cite

show abstract

“…Shan et al [22] introduced the CSI information of the uplink to enhance the CSI feature information of the downlink. Li et al [23] considered that CSI feedback has temporal characteristics, introduced a Long Short-Term Memory (LSTM) module, proposed a new compression and estimation structure, and developed an attention mechanism to sense local information and automatically weight feature information. Liu et al [24] proposed a CSI feedback framework based on deep learning with limited feedback and bidirectional reciprocal channel features.…”

Section: Introductionmentioning

confidence: 99%

A deep learning approach for reduce CSI feedback overhead in massive MIMO

Jianbin,

Jiamin

2024

Phys. Scr.

View full text Add to dashboard Cite

The Massive MIMO system in FDD communication mode is still one of the indispensable technologies in future cellular communication systems. In order to reduce CSI feedback overhead and enhance the quality of CSI channel reconstruction, this paper proposes a RiCsiNet network model and designs an iNetBlock module with larger convolutional kernels and a wider network structure. By connecting parallel convolution kernels of 1×1, 3×3, 5×5, and 7×7, both the width of the network and the receptive field are increased simultaneously, enabling calculation of different feature details at each layer. The compressed CSI is accurately estimated through residual connections at the BS end. The network model proposed in this paper, when considering both the model parameter size and the estimated CSI accuracy, outperforms the existing algorithm model in the NMSE index of 70%. In this paper, we verify that using different learning rate decay algorithms to train the model, a good learning rate decay algorithm can effectively improve the quality of the model, the best result is 12% higher than the worst result. Furthermore, we demonstrate that training different network models with varying amounts of data can not only save time but also maximize CSI channel estimation quality on the BS side. Finally, the RiCsiNet model was verified using different SNR under COST2100 channel model. QuaDRiGa data sets with different truncated subcarriers are used to verify the RiCsiNet model. The CSI estimated by the RiCsiNet model all showed high accur

show abstract

“…Even though the latter has reduced complexity with respect to the first structure, it is still more complex than CsiNet. One of the most recent advancements in DL is the concept of attention, which is exploited in [ 27 , 28 ]. In the former, long short-term memory (LSTM) is adopted to learn the temporal correlation of channels, while an attention mechanism is developed to perceive local information and automatically weight feature information.…”

Section: Introductionmentioning

confidence: 99%

Implementation of Deep-Learning-Based CSI Feedback Reporting on 5G NR-Compliant Link-Level Simulator

Riviello

Tuninato

Zimaglia³

et al. 2023

Sensors

View full text Add to dashboard Cite

Advances in machine learning have widened the range of its applications in many fields. In particular, deep learning has attracted much interest for its ability to provide solutions where the derivation of a rigorous mathematical model of the problem is troublesome. Our interest was drawn to the application of deep learning for channel state information feedback reporting, a crucial problem in frequency division duplexing (FDD) 5G networks, where knowledge of the channel characteristics is fundamental to exploiting the full potential of multiple-input multiple-output (MIMO) systems. We designed a framework adopting a 5G New Radio convolutional neural network, called NR-CsiNet, with the aim of compressing the channel matrix experienced by the user at the receiver side and then reconstructing it at the transmitter side. In contrast to similar solutions, our framework is based on a 5G New Radio fully compliant simulator, thus implementing a channel generator based on the latest 3GPP 3-D channel model. Moreover, realistic 5G scenarios are considered by including multi-receiving antenna schemes and noisy downlink channel estimation. Simulations were carried out to analyze and compare the performance with current feedback reporting schemes, showing promising results for this approach from the point of view of the block error rate and throughput of the 5G data channel.

show abstract

A Novel CSI Feedback Approach for Massive MIMO Using LSTM-Attention CNN

Cited by 15 publications

References 24 publications

Massive MIMO Systems for 5G Communications

Massive MIMO Systems for 5G Communications

A deep learning approach for reduce CSI feedback overhead in massive MIMO

Implementation of Deep-Learning-Based CSI Feedback Reporting on 5G NR-Compliant Link-Level Simulator

Contact Info

Product

Resources

About