On EE Maximization in D2D-CRN With Eavesdropping Using LSTM-Based Channel Estimation

Emergence of 5G and beyond promise development of several applications specific Internet-of-Things (IoT) services involving consumer electronics devices doing trustworthy intelligent operations. One such application is smart healthcare support in hospital or home premises where battery driven wearable wireless nodes collect patient data, transmit securely and seamlessly in cooperative communications for monitoring. To meet the goal, this work suggests device-to-device (D2D) communications, operated in cognitive radio network (CRN), protecting from eavesdropping by exploiting artificial intelligence driven channel state information (CSI) estimation. IoT devices (IoDs) harvest energy from radio frequency (RF) signals and transmit own data with relaying message of primary users (PUs). The goal is to maximize energy efficiency (EE) of IoDs satisfying the constraints of own data transmission rate, cooperative outage of PUs, and secrecy outage rate with self-powering. A long short term memory (LSTM) based CSI estimation on indoor complex D2D links is suggested and shows comparable performance on EE maximization and outage secrecy, when compared with known CSI. Simulation results show about 20% EE performance improvement at 7 dB signal-to-noise-ratio (SNR) over 8 dB SNR at the power splitting factor 0.5 and time switching factor 0.07 using LSTM based CSI.