A grey wolf optimization metaheuristic approach for resource allocation in internet of things

Resource allocation in Internet of Things enabled fog computing environments is a complex task due to dynamic workloads, heterogeneous resources, and strict quality-of-service requirements. This paper presents a Dual Grey Wolf Optimization framework for efficient resource allocation and task scheduling in fog-cloud environments. The proposed approach adopts a dual-island architecture that separates local fog and cloud fog resources, allowing cooperative optimization through periodic information exchange between the two search spaces. A mathematical model is developed by considering key factors such as processing time, communication delay, service availability, and task deadlines. The effectiveness of DGWO is evaluated through simulation and compared with Genetic Algorithm, Particle Swarm Optimization, Ant Colony Optimization, Grey Wolf Optimizer, Chaotic GWO, and Improved GWO. The results indicate that DGWO consistently achieves lower service latency and better resource utilization under varying workload and population settings. These findings suggest that the proposed DGWO framework offers a scalable and efficient solution for resource management in IoT-enabled fog computing environments.

Hali tarjima qilinmagan