Abstract:
Recently, simultaneous wireless information and power transfer (SWIPT) has emerged as a potential solution for improving energy efficiency. However, it is also unavoidabl...Show MoreMetadata
Abstract:
Recently, simultaneous wireless information and power transfer (SWIPT) has emerged as a potential solution for improving energy efficiency. However, it is also unavoidable to be eavesdropped on by security threats. In this paper, we investigate the secure transmission of the SWIPT system where a user is equipped with power-splitting (PS) scheme while an eavesdropper (Eve) tries to listen to the private information of the transmitter-user communication link. Our objective is to optimize the system secrecy rate while satisfying the requirements on energy harvesting (EH) at the user and transmit power at the transmitter. For solving the optimization problem, we utilize the feasible point pursuit (FPP) technique and the successive convex approximation (SCA) iterative-based algorithm. Although this algorithm can effectively solve our non-convex problem, it is often quite complex and time-consuming due to the many mathematical transformations and the need for the number of iterations to be converged to the optimal solutions. Therefore, we also consider the deep learning (DL)-based approach which helps the optimization problem to achieve an efficient solution in terms of the computation time. The simulation results validate the proposed scheme significantly improve the system secrecy rate. Moreover, the DL scheme achieved similar performance to the optimization algorithm, but with low computation time.
Published in: 2021 International Conference on Information and Communication Technology Convergence (ICTC)
Date of Conference: 20-22 October 2021
Date Added to IEEE Xplore: 07 December 2021
ISBN Information:
Print on Demand(PoD) ISSN: 2162-1233