Adaptive Resource Allocation for Service-Based Systems

Due to its major advantages, service-oriented architecture (SOA) has been adopted in various distributed systems, such as web services, grid computing systems, utility computing systems and cloud computing systems. These systems are referred as service-based systems (SBS). In order to effectively use these systems in various applications, one major challenge which must be addressed is to manage the quality of services (QoS) to satisfy users’ requirements. In SBS, multiple services are often hosted by the same server and compete for the limited system resources of the server, such as CPU-time, memory and network bandwidth. In addition, service compositions, resource status of servers, workflow priorities and QoS requirements are usually dynamically changing in runtime. Hence, it is necessary to have effective techniques to allocate the system resources to each service provided by a server in order to satisfy the QoS requirements of multiple workflows in SBS. In this paper, a resource allocation approach is presented to adaptively allocating the system resources of servers to their services in runtime in order to satisfy one of the most important QoS requirements, the throughput, of multiple workflows in SBS.     

Service for consistency management of replicas in data grid

Today, grid technology has evolved to the point where it is no longer a theory but a proven practice. It represents a viable direction for corporations to explore grid computing as an answer to their business needs within tight financial constraints. In general, grids enable the efficient sharing and management of computing resources for the purpose of performing large complex tasks. Data grid provides the data management features to enable data access, synchronization, and distribution of a grid. The main aim here is to ensure a efficient access and quality data, to improve the availability, and be able to continue delivering acceptable services. In such systems, these advantages are not yielded by means others than replication mechanisms. The effective use the replication technique involves several problems, in relation with the problem of the coherence maintenance of replicas. Our contribution consists new service for the consistency management in the data grid. This service combines between pessimistic and optimistic approaches, taking into account benefits of both approaches, to find a compromise between performance and quality. In addition, our service has been extended by a mechanism placement of replicas based on economics model.     

Editorial: Internetware in Motion

The Internet provides a global open infrastructure for exchanging and sharing of various resource all over the world. The rapid development and wide application of the Internet makes it a new mainstream platform to use, develop, deploy and execute software systems and applications. With the vision of "Internet as a computer", many technical initiatives such as pervasive computing, grid computing, service computing and cloud computing emerges on this open and dynamic environment. In order to support the various new application styles and accommodate the fundamental change of the underlying infrastructure, many specific software technologies such as service-oriented architecture are proposed for current practices. While these technologies are useful and widely accepted, they have not formed a systematic solution as matured as the object-oriented technology, as a uniformed software methodology and technology system is yet to be developed.     

网格计算技术及应用综述

Grid computing is a new kind of distributed computing technology and computing environment ,and also an attentive hot point of information technology in the world. It launches a space for new generation internal application,due to its supporting the complicated service efficiently and useable resource in the Internet. This paper sums up the results and applications instance in the grid computing in the world during recent years ,and then analyzes emphatically the system architecture ,components ,working principle in the grid computing and some typical grid systems ,and then discusses the problems of the large scale science computing and network service in grid computing in China,and alsopoints out the future trends.     

The 6th International Conference on Grid and Cooperative Computing

Recent years have seen rapid advances in various grid-related technologies, grid middleware as well as grid applications. The GCC conference has become one of the world-wide largest scientific events in the area of grid and cooperative computing. The 6th international conference on grid and cooperative computing （GCC2007） is to be held from August 16 to 18, 2007 in Urumchi, Xinjiang, China.     

Automatic Transaction Compensation for Reliable Grid Applications

Abstract As grid technology is expanding from scientific computing to business applications, service oriented grid computing is aimed at providing reliable services for users and hiding complexity of service processes from them. The grid services for coordinating long-lived transactions that occur in business applications play an important role in reliable grid applications. In this paper, the grid transaction service （GridTS） is proposed for dealing with long-lived business transactions. We present a compensation-based long-lived transaction coordination algorithm that enables users to select results from committed sub-transactions. Unlike other long-lived transaction models that require application programmers to develop corresponding compensating transactions, GridTS can automatically generate compensating transactions on execution of a long-lived grid transaction. The simulation result has demonstrated the feasibility of GridTS and effectiveness of the corresponding algorithm.     

Web Service Choreography: Unanimous Handling of Control and Data

To provide an effective service-oriented solution for a given business problem, it is necessary to explore all available options for providing the required functionality while ensuring a flawless data transfer within the composed services. Existing service composition approaches fall short of this ideal, as functional requirements and data mediation are not considered in a unified framework. We propose a service composition framework that addresses both of these aspects by integrating existing techniques in formal methods, service oriented computing and data mediation. Our framework guarantees the correct interaction of services in a composition by verifying certain behavioral constraints, and resolving data mismatches at semantic, syntactic and structural levels, in a unified manner. A tableau based algorithm is used to generate and explore compositions in a goal-directed fashion that proves or disproves the existence of a service choreographer. Data models, to detect and resolve data mismatches, are generated using WSDL documents and regular expressions. We also apply our framework to examples adapted from the existing service composition literature that provide strong testimony that the approach can be effectively applied in practical settings.     

A taxonomic framework for autonomous service management in Service-Oriented Architecture

Since Service-Oriented Architecture （SOA） reveals the black box nature of services, heterogeneity, service dynamism, and service evolvability, managing services is known to be a challenging problem. Autonomic computing （AC） is a way of designing systems that can manage themselves without direct human intervention. Hence, applying the key disciplines of AC to service management is appealing. A key task of service management is to identify probable causes for symptoms detected and to devise actuation methods that can remedy the causes. In SOA, there are a number of target elements for service remedies, and there can be a number of causes associated with each target element. However, there is not yet a comprehensive taxonomy of causes that is widely accepted. The lack of cause taxonomy results in the limited possibility of remedying the problems in an autonomic way. In this paper, we first present a meta-model, extract all target elements for service fault management, and present a computing model for autonomously managing service faults. Then we define fault taxonomy for each target element and inter-relationships among the elements. Finally, we show prototype implementation using cause taxonomy and conduct experi- ments with the prototype for validating its applicability and effectiveness.     

A taxonomic framework for autonomous service management in Service-Oriented Architecture

Since Service-Oriented Architecture (SOA) reveals the black box nature of services,heterogeneity,service dynamism,and service evolvability,managing services is known to be a challenging problem.Autonomic computing (AC) is a way of designing systems that can manage themselves without direct human intervention.Hence,applying the key disciplines of AC to service management is appealing.A key task of service management is to identify probable causes for symptoms detected and to devise actuation methods that can remedy the causes.In SOA,there are a number of target elements for service remedies,and there can be a number of causes associated with each target element.However,there is not yet a comprehensive taxonomy of causes that is widely accepted.The lack of cause taxonomy results in the limited possibility of remedying the problems in an autonomic way.In this paper,we first present a meta-model,extract all target elements for service fault management,and present a computing model for autonomously managing service faults.Then we define fault taxonomy for each target element and inter-relationships among the elements.Finally,we show prototype implementation using cause taxonomy and conduct experiments with the prototype for validating its applicability and effectiveness.     

基于网格计算技术的电力系统分布式并行计算——底层平台设计与实现

文章提出了基于网格计算来实现电力系统分布式并行计算的方案。主要涉及计算池(ComputingPool)的设计、资源的管理与动态分配,以及图论分割和稀疏数值计算库的设计和实现等。文章首先介绍了网格计算应用于电力系统分布式并行计算的概念,在此基础上,分析了基于GlobusR网格计算开发平台实现的以上功能模块。最后对测试平台和测试结果进行了简要的介绍。     

基于Globus Toolkit4的网格多资源Web服务实现

采用Globus作为事实上的网格基础平台,基于Globus进行网格服务开发是当前开发网格应用系统的主要手段.它提供了网格系统的基础服务,可以构建复杂的网格应用系统.针对GlobusToolkit4中网格服务的实现问题,介绍了单资源服务、多资源服务的实现模型,并以一个简单的网格计算为例,详细地说明了网格多资源Web服务的实现过程,最后成功地在单资源网格服务的基础上实现了网格多资源服务.     

网格计算环境下分布并行计算的一种实现方法

网格计算为人们处理很多复杂问题提供了新方法。文章利用GlobusToolkit来构建网格计算环境,并把它扩展为分布并行计算的支撑环境,为实现分布并行计算提供了新方法。讨论了任务分布、系统通信和容错机制等关键问题。最后给出了基于网格计算环境下的一个分布并行计算实例,取得了令人满意的实验结果。     

变电站网格监控研究

提出一种基于网格计算的变电站监控基础平台,该平台很好地利用了网格计算的分布式信息处理能力来处理广域变电站的监控问题.基于网格计算开发平台Globus来实现.实验室测试结果表明,该实验平台能够较好地完成系统数据的监控任务,为基于网格计算的变电站分布式监控的真正实施,提供了一种有效的模式.     

A computational economy for grid computing and its implementation in the Nimrod-G resource broker

Computational grids that couple geographically distributed resources such as PCs, workstations, clusters, and scientific instruments, have emerged as a next generation computing platform for solving large-scale problems in science, engineering, and commerce. However, application development, resource management, and scheduling in these environments continue to be a complex undertaking. In this article, we discuss our efforts in developing a resource management system for scheduling computations on resources distributed across the world with varying quality of service (QoS). Our service-oriented grid computing system called Nimrod-G manages all operations associated with remote execution including resource discovery, trading, scheduling based on economic principles and a user-defined QoS requirement. The Nimrod-G resource broker is implemented by leveraging existing technologies such as Globus, and provides new services that are essential for constructing industrial-strength grids. We present the results of experiments using the Nimrod-G resource broker for scheduling parametric computations on the World Wide Grid (WWG) resources that span five continents.     

基于网格的自适应错误检测算法

针对网格环境下应用的特殊性,设计了网格系统的错误检测模型,并主要对错误检测的核心——错误检测机制进行深入分析,提出一种自适应错误检测算法,该算法可以根据用户的需求为应用提供不同程度的错误检测服务,较好地满足了网格环境下应用的多样性和动态性。     

网格安全互操作及其应用研究

网格计算为地理分布资源的聚合以及大规模计算问题的解决提供了技术途径,国内外大型网格项目都是基于某种网格平台构建,通过这些平台管理着本领域的资源/服务,为了聚合不同网格平台管理的资源/服务,需要实现异构网格平台的互操作.由于不同网格平台的安全机制不同,安全互操作是网格互操作中需要解决的一个关键问题.通过分析,当前网格平台通常具有网格全局用户身份以及虚拟组织层次结构的公共特征,基于网格平台的主体类型研究网格平台互操作映射策略,并提出一种通用的安全互操作流程.CGSP和GOS是国内两大知名的网格中间件,分别管理了大量的教育和科技资源,以CGSP和GOS的安全互操作为例,阐述了安全互操作策略映射机制及安全互操作流程的具体实现,并分析了网格平台间的授权及其一致性、映射策略的灵活性以及互操作流程的安全性.最后,对CGSP和GOS的安全互操作的性能进行了测试分析.     

基于网格的并行FFT计算研究

快速傅里叶变换（FFT）在科学和工程领域有着广泛的应用。在网格环境下进行并行FFT计算可以提高运算速度,促进FFT的应用。在介绍了网格计算发展状况的基础上,详细阐述了基于网格的分布式并行计算。实验以FFT算法为背景,在Globus Toolkit 4平台下实现了并行FFT计算,并对实验数据作了分析,说明了基于网格的并行FFT计算的可行性。最后指出网格资源调度对并行计算的重要性。     

网格计算中一种基于属性的访问控制方法*

为了迎合目前网格计算对动态、细粒度授权的需求,针对网格资源分层式的组织结构特点,在现有的基于属性的访问控制（ABAC）模型的基础上,提出了一种针对网格资源的ABAC模型Grid_ABAC,并设计了基于XACML的Grid_ABAC实现框架,应用在GT4平台上。最后对GT4中的应用作了测试,测试结果表明授权结果与预期结果相同,且时间开销随着规模的增长并没有增长很多,在可接受范围内。证明Grid_ABAC模型在网格平台上具有一定的实用性。     

云计算研究

云计算模式是在基础设施即服务（IaaS）、平台即服务（PaaS）、软件即服务（SaaS）、分布式计算、并行计算和网格计算等概念演进并产生的结果。云计算模式是一种全新的计算应用模式,将会成为人们获取服务的主导方式。本文首先介绍云计算在业界中的概念,接着分析云计算和相关计算,最后关于云计算发展的前景进行展望。