A Q-learning-based QoS-aware multipath routing protocol in IoMT-based wireless body area network

2026-04-20 · Source: cs.AI updates on arXiv.org · Field: Technology & Digital — Artificial Intelligence & Machine Learning, Internet of Things (IoT) & Connected Devices · Depth: Expert, extended

Summary

A novel Q-learning-based QoS-aware multipath routing method, QQMR, has been developed for Internet of Medical Things (IoMT)-based Wireless Body Area Networks (WBANs). This method classifies sensed medical data into three categories: emergency, error-sensitive, and normal, each with distinct Quality of Service (QoS) requirements. QQMR employs an adaptive multi-level queuing model that dynamically adjusts queue capacities based on occupied volume, data arrival rate, and available buffer space. It also utilizes a QoS-aware clustering algorithm based on adaptive weighted fuzzy C-means to reduce state space and accelerate Q-learning convergence. The clustering output feeds into three independent Q-learning policies, each with its own Q-table, for specialized routing decisions. Simulation results in NS3, comparing QQMR against QQAR, EQRSRL, and QPRR, demonstrate that QQMR significantly improves packet delivery ratio (by 5.45% with varying node density and 2.48% with varying packet-sending rate) while reducing end-to-end delay (by 34.79% and 35.02%), routing overhead (by 11.17% and 11.73%), and energy consumption (by 19.08%).

Key takeaway

For AI Engineers designing routing protocols in IoMT-based WBANs, QQMR offers a robust framework to enhance network performance. You should consider implementing QoS-aware data classification and adaptive multi-level queuing to manage diverse medical traffic. Adopting state-space clustering with independent Q-learning policies can significantly reduce delay and energy consumption, improving overall packet delivery and network stability in dynamic healthcare environments.

Key insights

QQMR optimizes IoMT-based WBAN routing by combining QoS-aware clustering with specialized Q-learning policies for diverse medical data.

Principles

• Classify data by QoS requirements.
• Dynamically adjust queue capacities.
• Cluster state space to accelerate learning.

Method

QQMR classifies data, uses adaptive multi-level queuing, and applies QoS-aware weighted fuzzy C-means clustering to reduce state space. It then trains three independent Q-learning policies for emergency, error-sensitive, and normal packets, determining both primary and backup routes.

In practice

• Implement adaptive multi-level queuing for heterogeneous traffic.
• Utilize fuzzy C-means for QoS-aware network clustering.
• Design independent RL policies for different data priorities.

Topics

• Internet of Medical Things
• Wireless Body Area Networks
• Q-learning
• QoS-aware Routing
• Multipath Routing

Best for: AI Scientist, Research Scientist, AI Engineer

Related on AIssential

• A Q-learning-based QoS-aware multipath routing protocol in IoMT-based wireless body area network — QQMR uses Q-learning, fuzzy C-means, and multi-level queuing for QoS-aware multipath routing in IoMT WBANs.
• QG-MIL: A Gated Transformer Aggregator for Domain-Agnostic Multiple Instance Learning in Medical Imaging — QG-MIL stabilizes attention in MIL aggregators for medical imaging, improving prediction stability and cross-domain performance.
• Traj-Evolve: A Self-Evolving Multi-Agent System for Patient Trajectory Modeling in Lung Cancer Early Detection — Traj-Evolve combines non-parametric memory and parametric reinforcement learning for robust patient trajectory modeling in complex EHR data.
• HealthNLP_Retrievers at ArchEHR-QA 2026: Cascaded LLM Pipeline for Grounded Clinical Question Answering — A cascaded LLM pipeline improves grounded clinical question answering by integrating specialized modules.
• Decentralized Rank Scheduling for Energy-Constrained Multi-Task Federated Fine-Tuning in Edge-Assisted IoV Networks — A hierarchical federated fine-tuning framework optimizes LoRA rank selection for IoV, balancing accuracy, latency, and energy.
• Unlocking large scale AI training networks with MRC (Multipath Reliable Connection) — MRC improves large-scale AI training network reliability and performance through multipath packet spraying and static source routing.

Open in AIssential →

Editorial summary, takeaway, and curation by AIssential. Original article published by cs.AI updates on arXiv.org.