论文部分内容阅读
针对异构网格环境下依赖任务调度过程中网格节点行为可信性考虑不足的问题,根据网格节点的历史行为表现,构建了一个动态信誉度评估策略,为确立任务需求与资源节点行为可信属性之间的隶属关系,定义了隶属度函数,建立了一种安全可信的网格任务调度新模型.为了实现该模型,提出一种依赖任务可信调度的粒子群进化算法.该算法通过深度值和关联耦合度的引入解决了任务间的约束关系;为克服传统粒子群算法解决离散问题时的不足,结合网格任务调度问题的具体特点,重新定义并设计了新的粒子进化方程;为预防算法陷入局部最优,引入了均匀扰动速度.仿真实验表明,该算法与同类算法相比,在相同条件下具有较高的执行效率和安全可信优化性能等.
In order to solve the problem of insufficient trustworthiness of grid nodes in the task scheduling process in heterogeneous grid environment, a dynamic reputation evaluation strategy is constructed according to the historical behavior of grid nodes. In order to establish the task demand and resource node behavior, Credible attributes, the membership function is defined and a new safe and credible grid task scheduling model is established.In order to realize this model, a particle swarm optimization algorithm based on task trusted scheduling is proposed. In order to overcome the shortcomings of the traditional particle swarm algorithm in solving discrete problems, the algorithm redefined and designed a new particle evolution based on the specific characteristics of the grid task scheduling problem Equations are introduced to prevent the algorithm from falling into local optimum, and the uniform perturbation speed is introduced.The simulation results show that the proposed algorithm has higher execution efficiency, safe and credible optimization performance under the same conditions compared with similar algorithms.