A New Resource Allocation Technique in Vehicular Fog Computing Based Multi-Objective Optimization Algorithm with Latency Constraints and Energy Reduction

Abstract

Despite the fact that fog computing is a relatively young research area, there are effective and integrated methods for managing service activation and allocating 1oV services among the various fog computing service resources. In order to manage the scheduling and activation of fog computing services more effectively, this research suggests a multi-objective grey wolf optimization (MOGWO) method. The Modified Grey Wolf Multi-Objective Optimization (GMOGWO) algorithm also combines the Gravity Reference Point approach with MOGWO. It determines the ideal download location by taking into account two factors: computation time and energy usage in a multi-user, multi-crawl, scalable, and diverse environment. The proposed algorithm is extended and improved to examine resource statuses and management tasks, and multi-objective functions are used in the resource allocation process. The GWO approach is utilized to tackle the scheduling issue first, and container migration is used to resolve the resource and task distribution issues. Shutting down unused physical servers reduces power consumption, improves imbalance, lowers latency, and boosts efficiency.