【摘要】 研究运用投标模型对网格资源进行合理分配.建议了网格任务A gen t的投标方式,并提出了任务A gen t的爬坡式投标算法,任务A gen t可以通过该算法搜索效用函数获得其期望效用最大化.网格任务A gen t的效用函数是基于期望的效用函数.如果任务A gen t在限定的时间内完成所有的任务并且将剩余的费用归还,用户将表示满意,否则,用户表示不满意.在仿真实验中,着重研究了网格任务A gen t效用函数与作业响应时间之间的关系,并对基于效用函数的经济调度方法与传统的先来先服务(FCFS)方法进行了比较分析.更多还原

【Abstract】 This paper studies applying bid model to rationally allocation grid resources.It discusses grid task agent’s bidding scheme and proposes a grade-climbing algorithm for grid task agent.The task agent can maximize its expectation-based utility function through searching the right values of the utility function.The utility function of grid task agent is expectation-based function.If grid task agent can complete tasks within time limits and return surplus fund,grid user satisfies,otherwise,grid user doesn’t satisfy.In the simulation experiment,the relationship of grid task utility function and task response time is studied,the performance of utility function based economic scheduling method and conventional FCFS is also compared with and analyzed.更多还原