.png){kind=icon}
返回
Algorithms for reliability-oriented module allocation in distributed computing systems
.png){kind=icon}
PRE
AI
DOI：10.1016/S0164-1212(97)00005-8.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
We consider the problem of finding an allocation of program modules onto processors of a distributed computing system such that the reliability of successfully executing these modules is maximized. The distributed system consists of a number of processors interconnected by means of communication links. Certain constraints such as storage and load limits may be present at each processor. At any point of time, each component of the distributed system (processor or communication link) can exist in either of two states-operational or failed. The probability of a component being operational is given. A program module can be executed on any one of a set of processors. For execution, it requires access to certain data files. If a particular file it requires is not available locally, it has to access the file remotely, and for the remote access to be possible, at least one path (sequence of links and processors) from the processor at which the program module is executing, to one of the processors where the required file is available, must be operational. To improve reliability, there may be multiple copies of certain files, dispersed at various processors. Our aim is to allocate the program modules to processors in a manner that maximizes the probability of it being able to successfully access ail the files it requires for execution, and the allocation should not violate any of the constraints. This problem is known to be NP-hard. We use a state space search technique-the A* algorithm to obtain an optimal allocation. We also present a heuristic algorithm which obtains sub-optimal allocations in a reasonable amount of computation time. Through simulations over a wide range of parameters, we demonstrate the effectiveness of our approach. (C) 1998 Elsevier Science Inc.
Keyword:
TASK ALLOCATION
ASSIGNMENT
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
IF:
4.1
论文数:
5.5K
被引数:
8.4K
机构
暂无机构信息
引用论文
分享收藏分享收藏Diabetes is associated with increased risk for in-hospital mortality in patients with COVID-19: a systematic review and meta-analysis comprising 18,506 patients.png)
Hormones
OAAI
HormonesIF0
OAAI分享收藏Function of the Pseudomonas aeruginosa NrdR Transcription Factor: Global Transcriptomic Analysis and Its Role on Ribonucleotide Reductase Gene ExpressionPLOS ONE
OAAI
PLOS ONEIF0
OAAI分享收藏分享收藏
查看更多内容