Grey Wolf Optimizer-based Task Scheduling for IoT-based Applications in the Edge Computing

The growing data volume generated by IoT devices places considerable resource constraints on traditional cloud data centers, compromising their ability to cater to delay-sensitive IoT applications. The emergence of cloud-fog computing offers a potential solution, by extending cloud resources to the network edge. Yet, task scheduling in the cloud-fog environment introduces new challenges. Our study presents a semi-dynamic real-time task scheduling algorithm developed specifically for the cloud-fog environment, which efficiently allocates tasks while minimizing energy consumption, cost, and makespan. We utilized a modified grey wolf optimizer to optimize task allocation based on parameters like task length, resource requirements, and execution time. Compared to existing methods, including genetic algorithm, our algorithm demonstrates superior performance in terms of makespan, total execution time, cost, and energy consumption.