【24h】

Mobile Agent Based Adaptive Scheduling Mechanism in Peer to Peer Grid Computing

机译:点对点网格计算中基于移动代理的自适应调度机制

获取原文
获取原文并翻译 | 示例

摘要

In a peer to peer grid computing environment, volunteers are exposed to failures such as crash and link failures. In addition, since volunteers can dynamically join and leave executions and they are not dedicated only to a peer to peer grid computing, the executions of volunteers are stopped or suspended more frequently than in a grid computing environment. These failures result in the delay and blocking of the executions of tasks and even partial or entire loss of the executions. In addition, these failures make it difficult for a volunteer server to schedule tasks and manage the allocated tasks as well as volunteers. Existing peer to peer grid computing systems, however, do not deal with these failures in scheduling mechanisms. Moreover, since existing scheduling mechanisms are performed only by a volunteer server in a centralized way, there is a high overhead. To solve these problems, we propose a mobile agent based adaptive scheduling mechanism (MAASM). We implemented MAASM in Ko-rea@Home and ODDUGI mobile agent system. The MAASM reduces the overhead of volunteer server by using mobile agents in scheduling procedure in a distributed way. In addition, it tolerates the various fail-ures(especially, volunteer autonomy failures) which frequently occur in a peer to peer grid computing environment. Consequently, MAASM guarantees reliable and continuous executions in spite of the failures, so it decreases total execution time.
机译:在对等网格计算环境中,志愿者面临故障,例如崩溃和链接故障。此外,由于志愿者可以动态地加入和离开执行程序,并且他们不仅致力于点对点网格计算,因此与网格计算环境相比,志愿者的执行被更频繁地停止或暂停。这些失败导致任务执行的延迟和阻塞,甚至导致执行的部分或全部丢失。此外,这些故障使志愿者服务器和志愿者很难安排任务并管理分配的任务。但是,现有的对等网格计算系统在调度机制中无法处理这些故障。此外,由于现有的调度机制仅由志愿者服务器以集中方式执行,因此存在高开销。为了解决这些问题,我们提出了一种基于移动代理的自适应调度机制(MAASM)。我们在Ko-rea @ Home和ODDUGI移动代理系统中实施了MAASM。 MAASM通过在调度程序中以分布式方式使用移动代理来减少志愿者服务器的开销。此外,它可以容忍在对等网格计算环境中经常发生的各种故障(尤其是自愿自治故障)。因此,即使发生故障,MAASM仍可确保可靠且连续的执行,因此减少了总执行时间。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号