云环境中基于粒子群算法的任务调度研究

任务调度是云计算实现高效计算的关键技术。本文采用粒子群算法进行任务调度求解,对每个子任务占用的资源采用间接编码方式,考虑时间和成本定义合理的初始化参数,选择合适的适应度函数,尽量避免陷入局部最优。仿真结果表明,改进算法具有寻优能力强、耗时少等优点,实现较为理想的任务调度结果。

Task Scheduling Research Based on Particle Swarm Optimization Algorithm in Cloud Environment

Task scheduling is the key technology to achieve efficient computing in cloud computing. The particle swarm algorithm is used in this paper, and adopts indirect encoding method for each sub tasks and resources, define the initial parameter with considering time and cost reasonable, and appropriate fitness function, to avoid falling into local optimal. The simulation results show that, the improved algorithm has powerful optimizing ability, time-saving advantages, realize the task scheduling and the results are satisfactory