Cooperative Relay and Jammer Node Selection Strategies Based on Feed-Forward Neural Network

Cooperative non-orthogonal multi-access networking is a promising model for future wireless networks, due to its benefits in terms of energy efficiency, broader coverage and reducing interference. In this paper, under the presence of an eavesdropper node, we are researching the secrecy efficiency of a downlink cooperative non-orthogonal multi access (NOMA) communication system. This paper proposes a cooperative node based on deep learning feed forward neural network. The selected cooperative relay node is employed to enhance the channel capacity of the legal users, where the selected cooperative jammer is employed to degrade the capacity of the wiretapped channel. Simulations of the secrecy performance metric namely the secrecy capacity (C
s
) are presented and compared with the conventional technique based on fuzzy logic node selection technique. Based on our simulations and discussions the proposed technique outperforms the existing technique in terms of the secrecy performance.