This letter presents a novel deep reinforcement learning (DRL) approach for joint time allocation and power control in a cognitive Internet of Things (CIoT) system with simultaneous wireless information and power transfer (SWIPT). The CIoT transmitter autonomously manages energy harvesting (EH) and transmissions using a learnable time switching factor while optimizing power to enhance throughput and lifetime. The joint optimization is modeled as a Markov decision process under small-scale fading, realistic EH, and interference constraints. We develop a double deep Q-network (DDQN) enhanced with an upper confidence bound. Simulations benchmark our approach, showing superior performance over existing DRL methods.
@article{arxiv.2512.15062,
title = {Deep Reinforcement Learning for Joint Time and Power Management in SWIPT-EH CIoT},
author = {Nadia Abdolkhani and Nada Abdel Khalek and Walaa Hamouda and Iyad Dayoub},
journal= {arXiv preprint arXiv:2512.15062},
year = {2025}
}
Comments
Published in IEEE Communications Letters, 2025. This arXiv version is the authors' accepted manuscript