基于混合蚁群优化的边缘计算细粒度任务调度方法

Chen Gang? Wang Zhi-Jian

摘要:

为缓解中心服务器的压力，制定合理的调度方案，基于混合蚁群优化算法提出了边缘计算细粒度任务调度方法。描述边缘计算任务调度问题，并设置假设条件，简化调度求解难度。通过计算任务的优先指数，按照从大到小的顺序排列后组成任务队列。分析边缘服务器性能特征，明确边缘服务器处理能力。构建能耗以及时延多目标函数，并设置约束条件，利用混合蚁群优化算法求解多目标函数，完成边缘计算细粒度任务调度方案设计。结果表明：该方法应用下的任务调度能耗和时延更小，说明所提方法性能更优，所获得的调度方案更合理。

Abstract:

In order to alleviate the pressure of the central server and formulate a reasonable scheduling scheme, a fine-grained task scheduling method based on edge computing is proposed based on hybrid ant colony optimization algorithm. Describe the scheduling problem of edge computing tasks, and set assumptions to simplify the difficulty of scheduling. By calculating the priority index of tasks, the task queue is formed after being arranged in the order from large to small. Analyze the performance characteristics of edge server and clarify the processing capacity of edge server. The multi-objective function of energy consumption and delay is constructed, and some constraints are set. The multi-objective function is solved by hybrid ant colony optimization algorithm to complete the design of fine-grained task scheduling scheme for edge computing. The results show that the proposed method has less energy consumption and delay, which shows that the performance of the proposed method is better and the scheduling scheme is more reasonable.