Physical layer safety beam forming method based on linear neural network

Abstract

The present invention discloses a physical layer safety beam forming method based on a linear neural network. In a multi-input and mono-output system, the reciprocity of a channel is employed, a single antenna legal receiving terminal sends a training sequence, and multi-antenna sender security signals and an artificial noise beam forming weight are obtained through training of a neural network. The three processes of the channel estimation, the channel state information feedback and the beam forming design are combined into a reverse training process employing the linear neural network, onlyone training sequence is sent with no need for feedback, and therefore, compared to a traditional method, the method provided by the invention ensures the information transmission safety while reducing the complexity.

Description

technical field [0001] The invention belongs to the field of information communication, and specifically utilizes a linear neural network to design beamforming vectors of useful signals and artificial noise to realize confidential transmission of information. Background technique [0002] Physical layer security technology utilizes the time-varying, random, and reciprocal characteristics of wireless channels to realize the confidential transmission of information from the physical layer. Using signal processing technology to create and expand the difference in transmission quality between legitimate channels and eavesdropping channels, and obtaining confidentiality capacity is an important part of achieving physical layer security. The most commonly used technologies are multi-antenna beamforming technology and artificial noise-assisted interference technology. In physical layer security, the use of beamforming technology can increase the signal strength of legitimate users ...

AI Technical Summary

Problems solved by technology

There is feedback overhead in the CSI feedback link, and the capacity of the feedback channel will also limit the accuracy of feedback CSI. At the same time, there is also a bias in the channel estimation, which affects the performance of beamforming.

However, under the Multiple-Input Single-Output (MISO) channel, since there are multiple transmit antennas, the training sequences sent by each antenna must be orthogonal to each other when performing CSI estimation, and the channel overhead of sending the training sequences is relatively large. The receiving end needs to feed back the estimated CSI of multiple channels, and the feedback overhead is also very large, so it will have a great impact on the transmission efficiency of the system

Images