{"ID":2827850,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2512.15062","arxiv_id":"2512.15062","title":"Deep Reinforcement Learning for Joint Time and Power Management in SWIPT-EH CIoT","abstract":"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.","short_abstract":"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...","url_abs":"https://arxiv.org/abs/2512.15062","url_pdf":"https://arxiv.org/pdf/2512.15062v1","authors":"[\"Nadia Abdolkhani\",\"Nada Abdel Khalek\",\"Walaa Hamouda\",\"Iyad Dayoub\"]","published":"2025-12-17T04:00:58Z","proceeding":"eess.SP","tasks":"[\"eess.SP\",\"cs.NI\"]","methods":"[\"Reinforcement Learning\"]","has_code":false}