Exploiting TAS schemes to Enhance the PHY-security in Cooperative NOMA Networks: A Deep Learning Approach

Abstract

In this paper, we propose a novel antenna selection scheme to enhance the secrecy performance in a relay-aided non-orthogonal multiple access (NOMA) network against an eavesdropper. Different from the conventional antenna selection schemes that does not use channel information, the proposed antenna selection scheme can employ each channel information to maximize the main channel capacity and minimize the eaves-dropper channel capacity, respectively. In order to evaluate the secrecy performance, we propose a deep learning (DL)-based framework that can do real-time configuration since the DL-based framework is based on a compact mapping function. In detail, the proposed min-max relay transmit antenna selection (MMRTAS) scheme can improve the secrecy performance compared to that of the benchmark scheme. Numerical results show that the proposed MMRTAS scheme improves the secrecy performance compared to that of the benchmark scheme. The proposed DL-based framework can estimate the main channel and eavesdropper channel capacities for the near user and far user with an accuracy of 99.79%, respectively.