检索规则说明:AND代表“并且”;OR代表“或者”;NOT代表“不包含”;(注意必须大写,运算符两边需空一格)
检 索 范 例 :范例一: (K=图书馆学 OR K=情报学) AND A=范并思 范例二:J=计算机应用与软件 AND (U=C++ OR U=Basic) NOT M=Visual
机构地区:[1]中南大学信息科学与工程学院,长沙4100831
出 处:《系统仿真学报》2009年第12期3542-3548,共7页Journal of System Simulation
基 金:国家自然科学基金(60673165;60433020)
摘 要:在保障本地任务QoS需求并尊重网格节点本地调度策略的条件下,为网格用户提供QoS保障是计算服务网格环境中任务调度的一个重要目标和面临的新问题。根据对网格节点相关资源可用性历史数据进行统计、分析得出的结果,利用概率论方法对网格节点的资源能力进行评估,对网格节点状态进行划分并得到资源的平均状态;利用信息论中熵的概念对网格节点状态动态变化的不确定性进行评估并得到刻画网格节点状态不确定性的定量值。在此基础上,建立了一种基于性能评估的分布式调度框架,并提出了一种基于性能评估的网格任务调度算法。对GridSim进行了改进与扩展,基于改进与扩展后的GridSim对提出的算法进行仿真并与相关算法进行比较,实验结果表明了本所提出的调度算法在网格用户QoS保障程度、网格任务执行makespan以及负载均衡等方面的有效性。Meeting local job's QoS requirements and respecting local scheduling strategy of a Grid site, providing non-trivial QoS for Grid users is an important target and a new issue of task scheduling in Service Grid environment. Some researchers monitored resource availability characteristic in a Grid site, analyzed the trace file and obtained some statistical results. Some of these related previously work was grounded on and probability theory was utilized to evaluate resource performance of a Grid site. Several statuses of a Grid site were labeled and the average state was got within a period of time; the conception of entropy in information theory was employed to describe the uncertainty of resource. Then, a distributed resource- performance- evaluation-based framework was built and a performance-evaluation-based grid task scheduling algorithm was proposed. On the basis of extended and revised GridSim, extensive simulations were conducted and they were compared with two related algorithms. The experiment results demonstrate the effectiveness of the newly proposed algorithm in terms of users' QoS guarantee, Grid task makespan and load balance.
分 类 号:TP391.9[自动化与计算机技术—计算机应用技术]
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在链接到云南高校图书馆文献保障联盟下载...
云南高校图书馆联盟文献共享服务平台 版权所有©
您的IP:216.73.216.229