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

Abstract

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.