Abstract

Researchers are developing wearable air-borne infectious disease sensors. Since it is closer to IoT devices, the fog paradigm will boost real-time vital applications to fulfill cloud temporal limits like data throughput, response time, energy, etc. Real-time environments like intelligent healthcare monitoring suffer from inefficient load-balancing approaches for resource management at the fog layer, which reduces service quality and accelerates energy overuse. This paper proposes a fog-based Smart Infection Detection System (SIDS) architecture to control perilous infectious disease outbreaks before they spread and control pandemics such as COVID-19. An energy-efficient nature-inspired Geese Optimization Load Balancing Approach (GOLBA) is also proposed to dynamically select the closest, most active, and most resourceful computing machines to serve user requests and perform inter-cluster global and local load balancing. The proposed approach (GOLBA) outcomes are compared with the existing load balancing methods, such as the Fog Node Placement Algorithm (FNPA) and Round Robin (RR), to show its significance using the iFogSim simulator experimental setup. Analysis shows that GOLBA reduces response time by 6.6% and energy utilization by 8.9% compared to FNPA, 13.7%, and 15.1% compared to RR policy.