A hybrid PSO and GA algorithm with rescheduling for task offloading in device–edge–cloud collaborative computing

There have been some works proposing meta-heuristic-based algorithms for the task offloading problem in Device–Edge–Cloud Collaborative Computing (DE3C) systems, due to their better performance than heuristic-based approaches. But these works don’t fully exploit the complementarity of multiple meta-heuristic algorithms. In this paper, we combine the benefits of both swarm intelligence and evolutionary algorithms, for designing a high-efficient task offloading strategy. To be specific, our proposed algorithm uses the iterative optimization framework of Particle Swarm Optimization (PSO) to exploit the cognitions of swarm intelligence and applies the evolutionary strategy of Genetic Algorithm (GA) to preserve the diversity. In addition, to make full use of abundant cloud resources, we increase the probability of the cloud that a task is offloaded to, during each individual evolution. And to improve the overall acceptance ratio, we propose to reschedule tasks with deadline violations from their original assigned computing nodes to another ones with available resources for a task offloading solution. Extensive experiment results show that our proposed algorithm has better acceptance ratio and resource utilization than 13 classical and up-to-date methods, and verify the effectiveness and efficiency of our integration strategy and rescheduling scheme.