基于a+bi型联系数的不确定网格静态调度算法  

Static Scheduling Algorithms Based on Connective-number of Type a+bi for Uncertain Computing Grid

作　　者：黄德才[1] 张丽君[1] 赵克勤 

机构地区：[1]浙江工业大学信息工程学院,杭州310032 [2]诸暨市联系数学研究所,诸暨311811

出　　处：《计算机科学》2007年第8期126-129,179,共5页Computer Science

基　　金：浙江省自然科学基金资助项目(Y105118&Y105109)

摘　　要：任务调度算法是计算网格任务管理系统中的核心问题。由于网格环境中存在大量的不确定因素,导致传统网格调度算法和调度系统不能在开放、异构和动态的真实网格环境中有效运行。利用一种新的软计算方法——集对分析联系数研究和处理网格调度中的综合不确定性问题。在简单介绍集对分析概念和应用情况基础上,引入联系数概念、运算规律和全序关系,分别提出了基于联系数的不确定网格静态调度算法CBU—Min-min、CBU—Max-min和CBU—Surferage,并进行了数值仿真实验研究。理论和实验研究表明,这些算法能较好地描述网格任务预期执行时间的动态性和不确定性,并使传统网格调度方法成为其特例,在动态和不确定网格环境中有良好的理论和实际应用价值。Job scheduling algorithms are kernel technique in task management system of computing grid. Because the dynamic and uncertainty exist in grid environment, the traditional job scheduling algorithms cannot be applied effectively in the real open, heterogeneous and dynamic grid environment, and let the job scheduling system do not work well. Using connective number of Set Pair Analysis（SPA）, a new soft computation method to express ＆ process the synthetic uncertainty in task scheduling of the computing grid. After introducing SPA and its application briefly, present the definition of connective number, operational rules and total order relation suitable for computing grid scheduling, three static scheduling algorithms, CBU_Min-min, CBU_Max- min and CBU-Surferage, are presented for the uncertain computing grid. Theory analysis and numerical experiment illustrate that these algorithms can express the dynamics and uncertainty of expected time to compute of tasks in the computing grid environment, they are the generalization of traditional grid scheduling algorithms, and there are high value in theory and application in the dynamic and uncertain grid environment.

关 键 词：计算网格 不确定性 任务调度 调度算法 

分 类 号：TP393[自动化与计算机技术—计算机应用技术]