Augmentation Of Efficient Task Offloading In Mobile Edge Environments For Mobile Applications

Abstract

  Mobile edge computing (MEC) emerges as a cutting-edge technique that effectively alleviates the computational burden on mobile devices through task offloading. In the realm of Mobile Edge Computing (MEC) augmented by 5G technology, the process of delegating computing tasks from edge devices to edge servers within the edge network can significantly diminish latency. Overcoming the challenge of designing a well-balanced task offloading strategy in a resource-limited multi-user with MEC environment to address users' requirements remains a noteworthy concern. This paper introduces Greedy method based Genetic Algorithm (GA) for task offloading proportion, channel bandwidth, and Mobile Edge Servers' (MES) computing resources. The method is designed to handle scenarios where certain computing tasks can be partially offloaded to the MES. By considering the limitations imposed by wireless transmission resources and Edge servers' processing capacity, GA is employed to optimize the task completion time for users. The offloading strategy, which utilizes the combination of Greedy with GA, is evaluated and compared against both the genetic algorithm (GA) and the Greedy method through a series of simulation experiments demonstrates its effectiveness in reducing Energy Consumption, Delay time, and ensuring fairness in Resource cost for users' task completion times.