Design of an Efficient Bio-inspired Model for Efficient Fog Resource Management in IoT Environments

The ever-growing proliferation of Internet of Things (IoT) devices has necessitated the development of advanced fog computing frameworks for effective resource management and low-latency responses. While existing models offer certain advantages in task scheduling and resource allocation, there remains a significant room for improvement. In this paper, we introduce a novel optimization algorithm, Particle Swarm Elephant Herding Optimizer (PSEHO), inspired by the swarm intelligence of particles and the herding instincts of elephants, for optimizing the resource management in fog environments. Our model ingeniously maps IoT task metrics—such as make span, deadline, RAM, and memory requirements—with fog resources by considering attributes like bandwidth, number of processing elements, RAM, and MIPS performance. Through comprehensive simulations, we demonstrate that the PSEHO model significantly outperforms existing approaches, showing a 4.9% improvement in makespan, a 3.5% boost in deadline hit ratio, and an 8.5% increase in scheduling efficiency levels. The results underscore the efficacy of our bio-inspired approach in harnessing fog resources more efficiently for IoT environments, thereby providing a robust, scalable, and high-performance solution for future applications.