Research on Task Offloading Strategies in Edge Computing Environments

Edge computing fulfills the urgent need of users for low-latency and high-quality computing services by transferring tasks from end devices to the edge side of the network for processing through task offloading techniques. However, edge computing still faces many challenges during task offloading. Considering that most task offloading strategies only optimize a single objective, this paper constructs a multi-objective optimization task offloading model, which integrates multiple metrics such as task offloading failure rate, task processing time, and load balancing. In order to solve the optimal solution of this model, this paper proposes a hybrid meta-heuristic algorithm based on greedy random adaptive search procedure (GRASP) and genetic algorithm (GA), called GAGRA. experimental results show that compared with genetic algorithm, ant colony algorithm, and simulated annealing algorithm, GAGRA enhances the task offloading failure rate, the task processing time, and load balancing respectively by 4.28%, 4.94% and 5.02%. These results validate the effectiveness of the task offloading strategy proposed in this paper.