SLA-Priority Reinforcement Learning-Based Resource Allocation Framework for IoMT-Enabled Healthcare Fog Computing

NAGARJUN E; Dharamendra Chouhan

doi:10.36948/ijfmr.2026.v08i04.82826

SLA-Priority Reinforcement Learning-Based Resource Allocation Framework for IoMT-Enabled Healthcare Fog Computing

Author(s)	Mr. NAGARJUN E, Dr. Dharamendra Chouhan
Country	India
Abstract	The rapid growth of the Internet of Medical Things (IoMT) has improved real-time health monitoring, but it has also created serious challenges in latency, energy consumption, bandwidth use, and adaptive resource management. Traditional cloud-only architectures require patient data to travel to distant data centers, which increases response time and can reduce the usefulness of urgent clinical alerts. Fog computing addresses this problem by placing computation close to medical sensors and hospital gateways. However, fog nodes have limited resources, and healthcare workloads change continuously. To address this issue, this study proposes a reinforcement learning based resource allocation framework for healthcare fog environments. The proposed model observes CPU utilization, memory utilization, network latency, patient load, and module placement, then selects actions such as scaling, migration, load balancing, or maintaining the current allocation. The model is evaluated against deep-learning predictor allocation, tabular Q-learning, and DQN-style DRL policies implemented in the accompanying reproducible experiment. The proposed SLA-priority RL method achieves the best overall performance among the compared strategies. It records the lowest average latency of 78.57 ms, compared with 79.75 ms for DL predictor allocation, 80.00 ms for tabular Q-learning, and 79.50 ms for DQN-style DRL. It also achieves the lowest energy index of 341.92 J and maintains 0.00% SLA violations, while the DL predictor, tabular Q-learning, and DQN-style DRL methods record SLA violations of 0.82%, 0.86%, and 0.81%, respectively. These results indicate that the proposed reward design improves responsiveness, energy efficiency, and SLA reliability for healthcare fog resource allocation.
Keywords	Fog computing, IoMT, Healthcare resource allocation, Reinforcement learning, Latency reduction.
Field	Computer > Network / Security
Published In	Volume 8, Issue 4, July-August 2026
Published On	2026-07-02
DOI	https://doi.org/10.36948/ijfmr.2026.v08i04.82826

View / Download PDF File

E-ISSN 2582-2160

doi

CrossRef DOI prefix of IJFMR is 10.36948/ijfmr

Downloads

Research Paper Format Copyright Permission Form and Undertaking Form Cover Page Vol 8 Isu 3 Cover Page Vol 8 Isu 2 Cover Page Vol 8 Isu 2

All research papers published on this website are licensed under Creative Commons Attribution-ShareAlike 4.0 International License, and all rights belong to their respective authors/researchers.

CC-BY-SA

About IJFMR Fees & Payment Current Issue Publication Archive	Submit Research Paper Track Submission Status Publication Guidelines Publication Ethics Peer Review & Plagiarism	Join as a Reviewer Editors & Reviewers Reviewer Referral Program Get Reviewer Membership Certi.	Website/Journal Policies Usage Policy Content Policies Privacy Policy

Contact Us		+91-9687-828-838	editor@ijfmr.com

International Journal For Multidisciplinary Research

A Widely Indexed Open Access Peer Reviewed Multidisciplinary Bi-monthly Scholarly International Journal

SLA-Priority Reinforcement Learning-Based Resource Allocation Framework for IoMT-Enabled Healthcare Fog Computing

Share this