Deep Reinforcement Learning for Joint Time and Power Management in SWIPT-EH CIoT

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Abdolkhani, Nadia, Khalek, Nada Abdel, Hamouda, Walaa, Dayoub, Iyad
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908717920813056
author Abdolkhani, Nadia
Khalek, Nada Abdel
Hamouda, Walaa
Dayoub, Iyad
author_facet Abdolkhani, Nadia
Khalek, Nada Abdel
Hamouda, Walaa
Dayoub, Iyad
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2512_15062
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Deep Reinforcement Learning for Joint Time and Power Management in SWIPT-EH CIoT
Abdolkhani, Nadia
Khalek, Nada Abdel
Hamouda, Walaa
Dayoub, Iyad
Signal Processing
Networking and Internet Architecture
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.
title Deep Reinforcement Learning for Joint Time and Power Management in SWIPT-EH CIoT
topic Signal Processing
Networking and Internet Architecture
url https://arxiv.org/abs/2512.15062