Optimizing The Effective Task Offloading in Mobile Edge Computing for Mobile Applications Based on Genetic Algorithm with Grey Wolf Optimization

As 5G and the Internet of Things (IoT) advance swiftly, the conventional cloud computing structure faces difficulties in sustaining the growing demands of computation-intensive and latency-sensitive applications. In response, Mobile Edge Computing (MEC) has surfaced as a solution, facilitating the offloading of numerous IoT tasks to edge services. Addressing the challenge of assessing the consequences of unpredictable interconnections between vehicle users and Mobile Edge Computing (MEC) servers on decision-making for offloading, and preventing significant deterioration in offloading efficiency, is a crucial problem requiring resolution. In this paper introduces a decision-making mechanism for task offloading that combines Grey Wolf Optimization with a Greedy-based Genetic Algorithm. Initially, the computation offloading cost for a cloud-edge computing system is defined. Subsequently, the application of Grey Wolf Optimization transforms the task offloading process, facilitating the derivation of an optimal offloading strategy. The effectiveness of the offloading strategy, integrating Greedy with Genetic Algorithm and optimized by Grey Wolf Optimization, is assessed and compared with existing methods such as Greedy-GA through a series of simulation experiments. The results demonstrate its capability to reduce energy consumption, decrease delay time, and ensure fairness in resource costs for users' task completion times.