Massive MIMO CSI Feedback Based on Generative Adversarial Network

Tolba, Bassant; Elsabrouty, Maha; Abdu-Aguye, Mubarak G.; Gacanin, Haris; Kasem, Hossam M.

doi:10.1109/lcomm.2020.3017188

Cited by 32 publications

(25 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It can be known from Figure 6a that the proposed method improves the SNR by about 3-6 dB compared with the references [25] and [18]. Compared with the method in reference [27], the SNR is improved by about 0.2 dB gain. It can be seen from Figure 6b that when the BS antenna is 128, the proposed method improves the SNR by about 3-6 dB compared with the references [25] and [18].…”

Section: Performance Analysis Of the Proposed Methodsmentioning

confidence: 79%

“…Under the condition that the feedback compression ratio is the same, the BER performance and system capacity of single-user and multi-user massive MIMO systems are, respectively, simulated. The proposed method Reference [27] Reference [25] Reference [18] SNR (dB) The proposed method Reference [27] Reference [25] Reference [18] (b) With 128 antennas Performance analysis of bit error rate Figure 6 shows the BER performance of a single-user system with 64 antennas and 128 antennas at the BS side and 3 antennas at the receiving side as a function of the Signal to Noise Ratio (SNR) variation. It can be seen from Figure 6 that no matter whether the BS end has 64 or 128 antennas, the proposed method has better BER performance than the reference [27], [25] and [18] methods.…”

Section: Performance Analysis Of the Proposed Methodsmentioning

confidence: 99%

“…It is not difficult to get from Figure 7, no matter whether the BS end has 64 antennas or 128 antennas, the BER performance under the multiuser system has the same trend as the BER performance under the single-user system. The proposed method has better BER The proposed method Reference [27] Reference [25] Reference [18] (a) With 64 antennas The proposed method Reference [27] Reference [25] Reference [18] (b) With 128 antennas performance than other channel acquisition methods. Compared with reference [25] and [18], the SNR is improved by 3∼6 dB gain, and compared with reference [27], there is also a gain of about 0.3 dB.…”

Section: Performance Analysis Of the Proposed Methodsmentioning

confidence: 99%

“…This framework can significantly improve channel quality without increasing time complexity and obtain better system performance. Reference [27] proposed a new CSI network framework based on deep learning. The encoder in the network uses a generative countermeasure network to decompress at the receiving base station side, which improves the performance of acquiring channel state information.…”

Section: Related Workmentioning

confidence: 99%

See 3 more Smart Citations

Channel state information acquisition method of internet of things based on deep learning

Zhang¹

2021

The Journal of Engineering

View full text Add to dashboard Cite

As one of the key technologies of Internet of things (IoT), the accurate and efficient acquisition of CSI is an important part to support the high quality communication of IOT system. However, the current IOT system is massive and complex, and the traditional CSI acquisition method is difficult to meet its efficient information communication. To solve this problem, this paper proposes an improved CSI acquisition method based on bidirectional convolutional long and short-term memory networks (Bidirectional Convolutional Long Short-Term Memory, Bi-ConvLSTM) and attention mechanism. This method unifies the Bi-ConvLSTM-Attention network module to improve the encoder and decoder of the CSI-Net network model. Among them, the Bi-ConvLSTM module is mainly used to learn the time correlation between channel matrices. The attention mechanism module is used to calculate the soft probability distribution, so that the Bi-ConvLSTM network has the function of automatic weighting, thereby further improving the characterization ability of characteristic information. In the last part of the thesis, the proposed method is simulated and verified. Experimental results show that the proposed method exhibits excellent network performance in both single-user and multi-user massive MIMO system scenarios. Compared with the comparison method, the bit error rate performance and system capacity are improved by about 0.3-6 dB and 1.3-3.7 bps/Hz in the multi-user complex scene.

show abstract

Section: Performance Analysis Of the Proposed Methodsmentioning

confidence: 79%

Section: Performance Analysis Of the Proposed Methodsmentioning

confidence: 99%

Section: Performance Analysis Of the Proposed Methodsmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

See 2 more Smart Citations

Channel state information acquisition method of internet of things based on deep learning

Zhang¹

2021

The Journal of Engineering

View full text Add to dashboard Cite

show abstract

“…One of the important practical challenges in massive MIMO is the best utilization of this diversity at a low cost. Also, one of the most important parts in the implementation of massive MIMO is having channel status information (CSI) in the BS [15,16]. So, the CSI error can have a very important effect on the massive MIMO performance.…”

Section: Introductionmentioning

confidence: 99%

A New Cooperative and Distributed Antenna Structure in Massive MIMO‐NOMA Based on mmWave Transmission Scheme

Salehi

Parhizgar

Pesaran

2021

Wireless Communications and Mobile Computing

View full text Add to dashboard Cite

In this paper, we propose a new massive multiple-input multiple-output (MIMO) nonorthogonal multiple access (NOMA) system with a cooperative and distributed antenna structure based on a millimeter-wave (mmWave) transmission system. We proposed this method to obtain high energy efficiency (EE) and spectrum efficiency (SE) by using the mmWave transmission scheme. In the proposed system, the user selects a few nearby base stations (BS) to create a virtual cell to own the serving BS antenna set. We concentrate on the mmWave massive MIMO-NOMA scheme. In this scheme, a large number of BS antennas and users by uniform distributions (UD) are considered in a specific area. Also, we combine our proposed method by interleaving division multiple access (IDMA) and utilize the IMDA benefits for high-rate applications. The proposed transmission scheme significantly improves the performance output in terms of SE, EE, sum rate, and log sum rate, according to our simulation results.

show abstract