An enhanced healthcare IoT task scheduling using hybrid Q-NEH and CS-GW optimization in fog computing environment

Abstract

This research addresses the critical challenge of task scheduling in healthcare Internet of Things (IoT) environments using fog computing architecture. We propose a novel hybrid algorithm that combines Q-learning enhanced Nawaz-Enscore-Ham (Q-NEH) for task prioritization with a Cuckoo Search-Gray Wolf (CS-GW) optimization approach. The increasing deployment of healthcare monitoring devices generates massive amounts of time-sensitive data, necessitating efficient processing strategies that can handle multiple competing objectives including minimizing makespan, maximizing resource utilization, and ensuring energy efficiency. Our hybrid solution leverages Q-NEH’s adaptive learning capabilities for intelligent task ordering alongside CS-GW’s balanced exploration-exploitation mechanisms for optimization. Experimental evaluation conducted with varying workloads (100-600 tasks) across different fog node configurations (10-60 nodes) demonstrates that the proposed algorithm achieves superior performance compared to traditional approaches including Particle Swarm Optimization (PSO), Genetic Algorithm (GA), and Ant Colony (AC) optimization. The results show that our CS-GW implementation significantly reduced makespan compared to conventional methods, while the integration of Q-NEH further enhanced scheduling efficiency across all tested algorithms. The successful combination of reinforcement learning with nature-inspired optimization techniques provides a robust framework for addressing the complex scheduling demands of modern healthcare monitoring systems.

Date	17 Dec 2024
Original language	American English
Awarding Institution	École de technologie supérieure
Supervisor	Michel Kadoch (Supervisor)