摘要 异构网格环境的特点决定了其任务调度是受调度长度、安全性能及调度费用等多个因素制约的。该文根据网格资源调度的特点构造了一个安全效益函数和节点信誉度动态评估模型，并以此为基础建立了一个多目标约束的网格任务调度模型。利用隶属度函数将多目标函数转化为单目标模型，通过设计新的进化算子，从而提出一种遗传算法MUGA(Mode Crossover and Even Mutation Genetic Algorithm)进行求解，并对算法的收敛性进行了理论分析。仿真实验表明，在同等条件下该算法与同类算法相比，在任务调度长度、安全效益值、可信度及调度费用指标优化方面具有较好的综合性能。
Abstract：The characteristic of heterogeneous grid environment determines that the task scheduling is constrained by a number of factors such as the length of scheduling, the performance of security, the cost of scheduling and etc. Firstly, based on the characteristics of grid task scheduling, a security benefit function and an efficient node’s credibility dynamic evaluation model are constructed. Then a constrained multi-objective grid task scheduling model is proposed. Secondly, by using the subjection degree function, the multi-objective optimization is transformed into a single objective optimization issue. Thirdly, Through the design of new evolutionary operators, a new genetic algorithm is proposed. The convergence of this algorithm is analyzed. Simulation results show that the proposed algorithm is better than the compared ones in terms of the length of the task scheduling, security efficiency value, reliability and scheduling costs.
2010, Vol. 32 
