Efficient Task Offloading in Mobile Edge Environments for Mobile Applications using an Grey Wolf Optimization –An Comparative Study

Abstract

Efficient task offloading in resource-constrained multi-user Mobile Edge Computing (MEC) environments is a critical challenge. This paper aims to minimize task completion time and optimize resource utilization by proposing a novel hybrid approach. We integrate a Greedy method, which determines initial task offloading proportions based on user needs and resource availability, with a Genetic Algorithm (GA), which refines the offloading strategy to minimize overall task completion time. Furthermore, we enhance this hybrid approach by utilizing Grey Wolf Optimization (GWO) to optimize the offloading process by dynamically adjusting offloading parameters. This nature-inspired algorithm allows the system to better adapt to changing network conditions. Simulation experiments compare the performance of this GWO-enhanced Greedy+GA strategy against standalone Greedy and GA methods, as well as against a pure GWO approach. We also conduct an empirical analysis of computation offloading costs, considering factors like communication overhead, energy consumption, and processing delays. Simulation results demonstrate that the proposed hybrid approach achieves superior performance in minimizing task completion time and optimizing resource utilization.