Abstract:

Full-duplex can double the spectrum efficiency theoretically.Thus it can further improve the spectrum efficiency when it is used in the relay systems.Considering the residual self-interference and signal-to-noise ratio,a problem was set to maximize the security capacity by selecting the optimal relay.This optimization problem was transformed into multi-classification problem.Thus a convolutional neural network (CNN)-based intelligent relay selection scheme was proposed.In the design of the classification model,the CNN was used to extract the spatial correlation of the channel,and the dimension of the convolution kernel was related to the number of relays.The pooling layer was not used to preserve the matrix characteristics of the input features.The simulation results show that the proposed CNN-based intelligent selection classification model has high classification accuracy,and can obtain the same security performance as the traditional exhaustive search scheme,and the real-time performance is significantly improved.

Key words: full-duplex, relay selection, supervised learning, multi-classifier