A Multi-Objective Genetic Algorithm Based Load Balancing Strategy for Health Monitoring Systems in Fog-Cloud

Abstract

As the volume of data and data-generating equipment in healthcare settings grows, so do issues like latency and inefficient processing inside health monitoring systems. The Internet of Things (IoT) has been used to create a wide variety of health monitoring systems. Most modern health monitoring solutions are based on cloud computing. However, large-scale deployment of latency-sensitive healthcare applications is hampered by the cloud’s design, which introduces significant delays during the processing of vast data volumes. By strategically positioning servers close to end users, fog computing mitigates latency issues and dramatically improves scaling on demand, resource accessibility, and security. In this work, we describe a new load-balancing strategy based on the Strength Pareto Evolutionary Algorithm 2 (SPEA2) for distributing work among fog nodes in a large-scale health monitoring system. We ran comprehensive simulations in the iFogSim toolkit to verify the efficacy of the proposed method, comparing the results to the cloud-only implementation, the Fog Node Placement Algorithm (FNPA), the Load Balancing (LAB) scheme, and the Load Balancing Scheme (LBS) in terms of latency and network utilization. The proposed health monitoring system deployment drastically decreases latency and network use in comparison to cloud-only, FNPA, LAB, and LBS schemes.