基于分层和分组的移动网格资源选择算法  

Hierarchical and group-based resource selection algorithm

作　　者：李方云[1] 李春林[1] 李辉[1] 

机构地区：[1]武汉理工大学计算机科学与技术学院,武汉430070

出　　处：《计算机应用研究》2009年第12期4439-4441,共3页Application Research of Computers

基　　金：湖北省自然科学基金资助项目(2008CDB335);国家自然科学基金资助项目(60773211);教育部新世纪优秀人才计划资助项目(NCET-08-0806)

摘　　要：针对移动网格的特殊环境,利用统计学中多次线性回归函数提出一种基于分层和分组的移动网格资源选择算法,该算法考虑了移动设备电池能量低、移动性及其处理能力弱等特征。算法中将移动资源分成不同级别层次并分成K组,将任务同时分配到符合资源请求的n组(n<K)中,且同时执行。实例分析结果表明,该算法不但避免了由于资源的移动性或者电池能量的不足而导致任务执行结果无法反馈的情况,而且能加快任务与资源的匹配速度,支持异构环境中的容错性。As to the special environment of the mobile grid, this paper proposed a hierarchical and group-based resource selection algorithm that supported fault-tolerance in mobile grid and considered various characteristics of mobile devices. The proposed algorithm considered remaining battery power, mobility, and performance of mobile devices, calculated rank of mobile devices and classified to K groups, and then assigned a job to top-N groups which could follow the resource request concurrently for fault-tolerance. Result manifests that ranking and grouping of mobile devices prevent there is no results due to the powerless or mobility of mobile device whenever a job is submitted and speed up the matching between the task and resource.

关 键 词：资源选择 移动设备 移动网格 分组 剩余能量 算法 

分 类 号：TP301.6[自动化与计算机技术—计算机系统结构]