Towards sustainable and realtime wireless body area networks: Smart scheduling and session-specific design with deep reinforcement learning
Date
2025
Authors
Li, Shuang
Journal Title
Journal ISSN
Volume Title
Publisher
Abstract
Wireless body area networks (WBANs) are essential for real-time health monitoring and control but face key challenges: (1) sustaining energy efficiency under limited battery capacity, (2) ensuring information freshness by delivering timely and reliable status updates, and (3) managing conflicting performance requirements, such as energy consumption and information freshness.
To address these challenges, this thesis presents a series of optimal transmission designs for WBANs leveraging machine learning (ML) and deep reinforcement learning (DRL) technologies. First, we investigate energy-efficient transmission designs that minimize energy consumption for each transmission session. Second, we develop joint scheduling and transmission design strategies to minimize the age of information (AoI). Third, we propose multi-objective optimization (MOO) approaches to balance trade-offs among conflicting performance metrics. For each transmission design,
we formulate the corresponding optimization problem as a Markov Decision Process (MDP). Based on the characteristics of the state and action spaces, we develop tailored ML/DRL-based solutions to learn near-optimal transmission policies.
We highlight key trade-offs in transmission design and conduct comparative analyses through selected numerical examples. The results demonstrate the effectiveness of the proposed ML/DRL-based solutions in addressing complex transmission designs in WBANs, enabling energy-efficient and freshness-sensitive communication, and advancing the practical deployment of sustainable and real-time health monitoring systems.
Description
Keywords
Wireless Body Area Networks, Session-Specific Design, Age of Information, Deep Reinforcement Learning