Deep Reinforcement Learning for Joint Time and Power Management in SWIPT-EH CIoT
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.
Authors
- Walaa Hamouda (ORCID: https://orcid.org/0000-0001-6618-5851)
- Nada Abdel Khalek (ORCID: https://orcid.org/0000-0001-9024-5367)
- Nadia Abdolkhani (ORCID: https://orcid.org/0000-0002-2203-2877)
- Iyad Dayoub (ORCID: https://orcid.org/0000-0003-0910-4722)
Institutions
- Centre National de la Recherche Scientifique (FR)
- Institut Supérieur de l'Électronique et du Numérique (FR)
- Institut d'Electronique, de Microélectronique et de Nanotechnologie (FR)
- Concordia University (CA)
- Université Polytechnique Hauts-de-France (FR)
- École Centrale de Lille (FR)
Publication Details
- Journal
- IEEE Communications Letters
- Published
- 2025-01-29
- DOI
- https://doi.org/10.1109/lcomm.2025.3536182
- Citations
- 4
- Primary Topic
- Network Time Synchronization Technologies
- Type
- article
- Field-Weighted Citation Impact
- 5.95
Funders
- Natural Sciences and Engineering Research Council of Canada
- Fonds de recherche du Québec – Nature et technologies