检索结果-内蒙古大学图书馆

作者：朱文华东南大学

学位级别：硕士

网格计算是近年来兴起的一个研究热点，它发展了最初元计算的概念，旨在使互联网上的各种资源实现全面共享与协同，使整个因特网整合成一台巨大的“超级计算机”。网格资源主要具有分布性、异构性和动态性等基本特点，这些特点给实现可... 详细信息

网格计算是近年来兴起的一个研究热点，它发展了最初元计算的概念，旨在使互联网上的各种资源实现全面共享与协同，使整个因特网整合成一台巨大的“超级计算机”。网格资源主要具有分布性、异构性和动态性等基本特点，这些特点给实现可靠、可伸缩和动态适应的网格计算带来了挑战。\n Jini是一种基于Java语言的处理动态分布式计算问题的简单的解决方案，其核心理念是实现快速配置的分布式计算环境，它提供了一个主动的响应式的分布式基础设施[13]。\n javaspaces则是一种基于Java语言的元组空间技术。本文较为详细的阐述了的Jini体系结构和javaspaces计算模型，并讨论了这两种分布式计算技术对于网格计算的适用性；基于Jini和javaspaces技术的分布式并行计算服务的精髓，提出了一个轻量级的网格计算平台原型系统的体系结构；讨论了原型系统设计和实现过程中需要解决的几个关键问题，包括动态Java类加载机制、任务分配机制、容错机制、问题分割以及安全性等问题；实现了网格计算平台原型系统并在此基础上设计了一套简单的网格编程接口，开发实现了简单的应用实例，并作了性能分析。该原型系统具有下列特点：\n ①基于网格原理，充分利用网络的闲置资源进行并行计算，解决“大”的计算问题(Job)，明显的加快了计算速度，缩短了对用户的响应时间；\n ②采用了Master接收用户Job、分解Job、写入javaspaces的机制，使得Master服务表现出多种角色：既提供接收Job的功能，又提供把任务写入javaspaces的功能；既能分解Job，又能合并Job的计算结果；\n ③闲置的计算资源以Worker的形式对外共享，Worker不需要注册，因此不需要发现、调度Worker参加计算。愿意贡献计算能力的Worker主动找到javaspaces、主动查找任务、主动进行计算，体现了“即插即用”的原则，系统具有一定的伸缩能力，而且降低了在资源发现、调度中的代价；\n ④基于租约机制，原型系统的运行具有一定的容错能力；原型系统可以有效的利用网络中闲置的具有分布、异构和动态变化等特性的计算资源，并具有一定平衡负载的能力；\n ⑤可移植性：原型系统基于Java平台，因此具有很好的移植性。\n 本文最后还指出了下一步需要进行的工作：原型系统需要进一步扩展能够解决问题(Job)的类型，研究分解和结果合并的各种算法；原型系统还应该为用户提供一个图形化的编程接口，方便用户提交计算任务；原型系统还需要进一步考虑与其它网格计算系统的互操作以及实现各种资源的共享与协作。

关键词：网格计算 Jini javaspaces 闲置计算资源分布式计算

来源：评论

学校读者我要写书评

暂无评论

基于javaspaces分布式计算技术的应用研究

基于JavaSpaces分布式计算技术的应用研究

引用

作者：于海征新疆大学

学位级别：硕士

计算机和网络技术的迅猛发展,大大提升了分布式计算在计算机科学领域中的重要性和地位。分布式计算的目标是把多台联网的计算机统一起来,让它们共享信息或其他资源,包含多媒体系统、客户-服务器系统、并行计算、Web 编程、移动agent 等... 详细信息

计算机和网络技术的迅猛发展,大大提升了分布式计算在计算机科学领域中的重要性和地位。分布式计算的目标是把多台联网的计算机统一起来,让它们共享信息或其他资源,包含多媒体系统、客户-服务器系统、并行计算、Web 编程、移动agent 等等。目前,信息处理中的巨大数据量影响着处理的速度,利用并行方式处理巨大数据量的信息成为重要的途径。采用分布式并行计算技术在加快信息的处理速度和提高效率方面得到了广泛的应用。本论文主要研究了分布式计算环境中的并行处理的方法,并在数字图像复原处理中得到应用。采用了Jini 技术中一个重要的工具集javaspaces 实现分布式并行计算,把BNM 图像复原串行算法改为并行算法,在javaspaces中得以实现。

关键词：分布式计算并行计算 javaspaces 图像复原

来源：评论

学校读者我要写书评

暂无评论

一个理想的分布式系统架构——javaspaces

一个理想的分布式系统架构——JavaSpaces

引用

中国航空学会信号与信息处理分会全国第二届联合学术交流会议

作者：孙剑陈英严伟李佳北京理工大学计算机系

总所周知,分布式系统在广泛的领域中得到发展.分布计算的思想被应用到数据库系统、文件系统、操作系统和通用环境等.本文的内容包括有对分布式系统的概述和javaspaces技术的介绍.javaspaces技术是用来解决分布地、持久地存储数据和分布... 详细信息

总所周知,分布式系统在广泛的领域中得到发展.分布计算的思想被应用到数据库系统、文件系统、操作系统和通用环境等.本文的内容包括有对分布式系统的概述和javaspaces技术的介绍.javaspaces技术是用来解决分布地、持久地存储数据和分布式计算的设计的问题.用户可以执行简单的操作来向javaspaces中写新项目、查询已有项目和删除已有项目.使用这些工具,我们可以向系统中写,以完成存储状态.还可以向使用数据流执行分布式算法的系统中写,并且让javaspaces为你执行分布式的持续存储.分布式数据结构的概念是可以被多个进程同时访问、操作的数据结构.大部分的计算环境都把数据引藏在中心管理过程的后面,而javaspaces技术却很容易支持分布式数据结构.

关键词：分布式系统分布式计算 javaspaces 租借计算机网络数据结构

来源：评论

学校读者我要写书评

暂无评论

A P2P tuple space implementation for disconnected MANETs

引用

PEER-TO-PEER NETWORKING AND APPLICATIONS 2015年第1期8卷 87-102页

作者： Benchi, Abdulkader Launay, Pascale Guidec, Frederic Univ Bretagne Sud IRISA Vannes France

Disconnected mobile ad hoc networks (or D-MANETs) are partially or intermittently connected wireless networks, in which continuous end-to-end connectivity between mobile nodes is not guaranteed. The ability to self-form and self-manage brings great opportunities for D-MANETs, but developing distributed applications capable of running in such networks remains a major challenge. A middleware system is thus needed between network level and application level in order to ease application development, and help developers take advantage of the unique features of D-MANETs. The characteristics of D-MANETs favor a middleware which supports a decoupled and opportunistic style of computation. Such requirements are perfectly addressed in the concept of Tuple Space. In this paper, we introduce a peer-to-peer javaspaces implementation that we specifically designed for D-MANETs, and with which pre-existing or new javaspaces-based applications can be easily deployed in such networks.

关键词： Peer-to-peer computing Opportunistic networking D-MANETs Coordination middleware javaspaces Future object

来源：评论

学校读者我要写书评

暂无评论

MADAMS: A software architecture for the management of networked measurement services

引用

COMPUTER STANDARDS & INTERFACES 2006年第4期28卷 396-411页

作者： Cicirelli, F Furfaro, A Grimaldi, D Nigro, L Pupo, F Univ Calabria Lab Ingn Software Dipartimento Elettron Informat & Sistemist I-87036 Arcavacata Di Rende CS Italy

MADAMS (Management Architecture for Distributed meAsureMent Services) is a novel service-based software framework designed for publishing, retrieving, configuring, setting up, monitoring and executing distributed measurement services over the Internet. The basic building block is the measurement service, i.e. a software object properly configured and made remote accessible across a network. A measurement service corresponds either to a single (virtual or physical) instrument, or to a collection of measurement services abstracting a test method. Service attributes include the graphical interface which supports user interactions. MADAMS is especially tuned to: (i) defining a common way to manage and use distributed measurement services, (it) introducing a data-exchange layer for inter-instrument communications, (iii) exploiting a design pattern which separates definition of service functionalities from distribution concerns. This paper introduces MADAMS, outlines its current implementation which depends on Java/Jini, and shows its application to a demand monitoring-control measurement system. (c) 2005 Elsevier B.V. All rights reserved.

关键词： networked measurement systems services middleware jini javaspaces Internet

来源：评论

学校读者我要写书评

暂无评论

Improved parallel implementation of the two-dimensional Ising model

引用

COMPUTER PHYSICS COMMUNICATIONS 2001年第3期141卷 313-321页

作者： Knoll, P Mirzaei, S Univ Vienna Dept Expt Phys A-1010 Vienna Austria

Some simulations we would like to perform in computational physics require so much computation time that it is not possible to finish them in reasonable length of time on any nowadays available computer. If it is possible to decompose a compute intensive problem into smaller independent tasks one possibility is to shorten the calculation time is to apply a parallel algorithm. Java, a platform independent programming language changed the way of software design by using Jini and javaspaces. new technologies that have been introduced recently. By applying javaspaces, a virtual, network accessible space can be used to store Java objects but also for effective parallel processing. In this paper, we report a novel, parallel implementation of the two-dimensional Ising model using the javaspaces technology. Our new approach was implemented on standard computer equipment and results in significant improvement of computation time. (C) 2001 Elsevier Science B.V. All rights reserved.

关键词： parallel algorithm Ising model Jini javaspaces

来源：评论

学校读者我要写书评

暂无评论

On load balancing approaches for distributed object computing systems

引用

JOURNAL OF SUPERCOMPUTING 2004年第2期27卷 149-175页

作者： Cheung, LS Kwok, YK Univ Hong Kong Dept Elect & Elect Engn Hong Kong Hong Kong Peoples R China

Distributed object computing systems are widely envisioned to be the desired distributed software development paradigm in the near future due to the higher modularity and the capability of handling machine and operating system heterogeneity. Indeed, enabled by the tremendous advancements in processor and networking technologies, complex operations such as object serialization and data marshalling become very efficient, and thus, distributed object systems are being built for many different applications. As the system scales up ( e. g., with larger number of server and client objects, and more machines), a judicious load balancing system is required to efficiently distribute the workload (e.g., the queries, messages/objects passing) among different servers in the system. Several such load balancing schemes are proposed recently in the literature. However, while the rationales and mechanisms employed are dramatically different, the relative strengths and weaknesses of these approaches are unknown, making it difficult for a practitioner to choose an appropriate approach for the problem at hand. In this paper, we describe in detail three representative approaches, which are all practicable, and present a quantitative comparison using a real experimental distributed object computing platform. Among these three approaches, namely, javaspaces based, request redirection based, and fuzzy decision based, we find that the fuzzy decision-based algorithm outperforms the other two considerably under a wide range of different practical scenarios.

关键词： distributed object computing load balancing Java javaspaces fuzzy decision Web servers request redirection

来源：评论

学校读者我要写书评

暂无评论

A distributed JAVASPACE implementation for HARNESS

引用

JOURNAL OF PARALLEL AND DISTRIBUTED COMPUTING 2000年第10期60卷 1325-1340页

作者： Migliardi, M Schubiger, S Sunderam, V Emory Univ Dept Math & Comp Sci Atlanta GA 30322 USA Univ Fribourg IIUF CH-1700 Fribourg Switzerland

HARNESS is an experimental metacomputing system based upon the principle of dynamically reconfigurable, object-oriented, networked computing frameworks. HARNESS supports reconfiguration not only in terms of the computers and networks that comprise the virtual machine, but also in the capabilities of the VM itself. These characteristics allow the construction of modular programming environments that can be plugged into the HARNESS system on demand. As a proof of concept exercise, and also with an intent to provide a flexible coordination facility for the HARNESS system, Sun's JAVASPACE interface was implemented as a HARNESS plug-in. The javaspaces model is part of the JAVA distributed computing effort and is essentially an object-oriented tuple-space. javaspaces technology is a simple unified mechanism for dynamic communication, coordination, and sharing of objects between JAVA technology-based network resources. This paper introduces the HARNESS system and discusses design, implementation, and preliminary experiences with the JAVASPACE for HARNESS. (C) 2000 Academic Press.

关键词： reconfigurable metacomputing systems flexible programming environment pluggable frameworks distributed components PVM javaspaces

来源：评论

学校读者我要写书评

暂无评论

Validation of a parallel genetic algorithm for image reconstruction from projections

引用

JOURNAL OF PARALLEL AND DISTRIBUTED COMPUTING 2003年第3期63卷 356-359页

作者： Knoll, P Mirzaei, S Ludwig Boltzmann Inst Nucl Med & Endocrinol Dept Nucl Med Wilhelminenspital A-1171 Vienna Austria Ludwig Boltzmann Inst Nucl Med & Endocrinol PET Ctr Wilhelminenspital A-1171 Vienna Austria

The problem of accurate image reconstruction from projections has repeatedly arisen over the last decades in a large number of scientific, medical and technical fields. Reconstruction algorithms use data from electron microscopes to reconstruct molecular structures or X-ray projection data to compute medical images. Usually, the applied projection data are noisy and therefore iterative algorithms are used to solve numerically a number of equations. Theory and empirical results demonstrate that genetic algorithms (GA) can accurately solve a broad class of problems, especially if noisy input data are used. GA are based on the evolution of random tries by individuals, and therefore the time to find an appropriate solution is rather long. In this work, we use a parallel approach using javaspaces to speed up a genetic reconstruction algorithm. (C) 2003 Elsevier Science (USA). All rights reserved.

关键词： parallel genetic algorithm reconstruction image processing javaspaces

来源：评论

学校读者我要写书评

暂无评论

A general architecture for demand migration in a demand-driven execution engine in a heterogeneous and distributed environment

A general architecture for demand migration in a demand-driv...

引用

3rd Annual Conference on Communication Networks and Services Research

作者： Vassev, E Paquet, J Concordia Univ Dept Comp Sci & Software Engn Montreal PQ H3G 1M8 Canada

ISBN: (纸本)0769523331

This article is an overview of the GIPSY Demand Migration System (DMS). This system brings a Demand Driven Execution Engine like the one used in the GIPSY to a high level of distributiveness and interoperability of operational nodes, by mixing together advanced distributed technologies. The main Demand Migration System's artifacts are discussed, and their different distributions within the GIPSY are surveyed. The article concludes with a presentation of a successful GIPSY Demand Migration implementation, based on JINI. This paper describes only the aspects of the GIPSY Demand Migration, i.e. it does not deal with load balancing and efficiency aspects of the GIPSY, as these are to be tackled by other subsystems of the GIPSY.

关键词： GIPSY distributed computing JIM javaspaces demand-driven execution

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：