雾计算平台的任务调度算法研究

Research on Task Scheduling Algorithm of Fog Computing Platform

摘要:

雾计算平台中的任务调度问题是无法在多项式时间复杂度内求取精确解的NP-问题。本文在根据雾计算任务调度流程,构建雾计算平台任务调度数学模型基础上,采用改进人工蜂群算法,将任务调度映射为蜂群寻找蜜源的过程,在种群初始化阶段过引入混沌思想,改善了人工蜂群算法缺陷,扩大了蜂群搜索范围,避免陷入局部最优解。实验结果表明,改进后的人工蜂群算法具有更快的算法收敛速度,算法解析所对应的任务调度策略,也具有更高的任务处理总性能,表明本文所研究的改进人工蜂群算法,达到了提高雾计算资源利用率,提高雾计算任务处理效率的目的。

Abstract:

The task scheduling problem in fog computing platform is a NP- problem which can"t get the exact solution in polynomial time complexity. Based on the process of task scheduling of fog computing and the mathematical model of task scheduling of fog computing platform, this paper uses the improved artificial bee colony algorithm to map task scheduling to the process of bee colony searching for honey source, introduces chaos thought in the initial stage of population, improves the defect of artificial bee colony algorithm, expands the range of bee colony search, and avoids falling into local optimal solution. The experimental results show that the improved artificial bee colony algorithm has faster convergence speed, the corresponding task scheduling strategy of the algorithm solution, and the higher overall performance of task processing. It shows that the improved artificial bee colony algorithm studied in this paper has achieved the purpose of improving the utilization rate of fog computing resources and the efficiency of fog computing task processing.