摘要
云计算可以通过即付即用的方式向用户工作流提供资源;为了解决资源服务代价异构环境下的云工作流任务调度代价问题,提出一种基于改进粒子群算法的云工作流任务调度算法WSA-IPSO;通过综合考虑任务的执行代价和依赖任务间发生数据传输时的通信代价,算法将总代价优化问题形式化为有向无环图DAG中的任务调度模型,并提出基于改进粒子群算法的优化模型对其进行求解;通过改进传统粒子群算法的粒子速度更新策略和惯性权重更新策略,算法可以以更快的收敛速度得到代价最小化的调度方案;通过仿真实验,与MCT算法及标准粒子群算法进行性能比较;实验结果表明,WSA-IPSO算法在降低总代价、任务分布的负载均衡以及算法收敛性方面比较同类算法均表现出更好的性能。
Cloud computing can provide resource for user＇ s workflow by the a pay per--use basis. To solve the scheduling cost optimi zation of cloud workflow tasks in dynamic resource service prices environment, a cloud workflow tasks scheduling algorithm based on im proved particle swarm optimization WSA IPSO was proposed. WSA IPSO considered comprehensively the execution cost of tasks and the communication cost between dependent tasks when they transferred data, formalised the optimization of total cost as a task scheduling model in DAG and presented an improved PSO algorithm to solve. Through improving the particle velocity updating strategy and inertia weight up- dating strategy of traditional partilce swarm optimization algorithm, the algorithm can obtain the scheduling scheme minimizing the execution cost with a faster convegence speed. The proposed algorithm was compared with MCT and standard particle swarm optimization algorithm by simulation experiments. The experimental results showed that WSA IPSO performed better in reducing total cost, load balance of tasks dis- tribution and convergence.
出处
《计算机测量与控制》
2017年第6期162-166,共5页
Computer Measurement &Control
基金
国家自然科学基金项目(51405349)
关键词
云计算
工作流
任务调度
粒子群算法
cloud computing
workflow
task scheduling
particle swarm optimization
