Adaptable Decentralized Service Oriented Architecture

In the Service Oriented Architecture (SOA), BPEL specified business processes are executed by non-scalable centralized orchestration engines. In order to address the scalability issue, decentralized orchestration engines are applied, which decentralize BPEL processes into static fragments at design time without considering runtime requirements. The fragments are then encapsulated into runtime components such as agents. There are a variety of attitudes towards workflow decentralization; however, only a few of them produce adaptable fragments with runtime environment. In this paper, producing runtime adaptable fragments is presented in two aspects. The first one is frequent-path adaptability that is equal to finding closely interrelated activities and encapsulating them in the same fragment to omit the communication cost of the activities. Another aspect is proportional-fragment adaptability, which is analogous to the proportionality of produced fragments with number of workflow engine machines. It extenuates the internal communication among the fragments on the same machine. An ever-changing runtime environment along with the mentioned adaptability aspects may result in producing a variety of process versions at runtime. Thus, an Adaptable and Decentralized Workflow Execution Framework (ADWEF) is introduced that proposes an abstraction of adaptable decentralization in the SOA orchestration layer. Furthermore, ADWEF architectures Type-1 and Type-2 are presented to support the execution of fragments created by two decentralization methods, which produce customized fragments known as Hierarchical Process Decentralization (HPD) and Hierarchical Intelligent Process Decentralization (HIPD). However, mapping the current system conditions to a suitable decentralization method is considered as future work. Evaluations of the ADWEF decentralization methods substantiate both adaptability aspects and demonstrate a range of improvements in response-time, throughput, and bandwidth-usage compared to previous methods.     

面向服务的网格资源管理模型研究*

开放网格服务体系结构(OGSA) 的出现表明让网格资源以服务形式提供标准化的接口已成为趋势,以前的资源管理模式已经不能满足应用的要求。为此,提出了一种面向服务的作业管理机制,它为用户提供透明的、与资源物理位置无关的并带有会话支持的作业服务接口,还引入了服务分级的概念来表示用户需求的不同网格服务级别,作业管理系统则根据可定制的服务级别,将各项QoS 特性映射到具体的作业管理行为。最后以电子政务为例,初步构建了该模型的原形系统。     

一种面向服务的网格工作流调度算法

面向服务的网格工作流的研究已成为网格领域的研究热点。由网格服务：组成的工作流（GSF）的调度问题是一个典型的NP问题,由于遗传算法具有并行性和全局解空间搜索的特点,非常适合解决这个问题。因此,本文首先给出GSF的GA定义,然后提出基于遗传算法的网格服务工作流调度算法GSFGA,并通过应用实例验证了该算法优于传统的调度算法,作为结论本文指出了下一步的研究工作。     

End-to-End QoS Support for a Medical Grid Service Infrastructure

Quality of Service support is an important prerequisite for the adoption of Grid technologies for medical applications. The GEMSS Grid infrastructure addressed this issue by offering end-to-end QoS in the form of explicit timeliness guarantees for compute-intensive medical simulation services. Within GEMSS, parallel applications installed on clusters or other HPC hardware may be exposed as QoS-aware Grid services for which clients may dynamically negotiate QoS constraints with respect to response time and price using Service Level Agreements. The GEMSS infrastructure and middleware is based on standard Web services technology and relies on a reservation based approach to QoS coupled with application specific performance models. In this paper we present an overview of the GEMSS infrastructure, describe the available QoS and security mechanisms, and demonstrate the effectiveness of our methods with a Grid-enabled medical imaging service.     

面向服务的网格软件测试环境

作为保证网格服务质量的重要技术手段,网格软件测试已成为网格研究的热点内容.作为开放的体系结构,SOA(service oriented architecture)为网格技术研究提供了有效的方法和手段.分析研究了面向服务的网格软件测试关键技术,重点从网格服务测试、网格性能测试和网格软件测试管理3个方面探讨了网格软件测试环境的构建.     

一种支持端到端QoS的服务网格体系结构

随着网格技术研究和应用的不断深入,缺乏服务质量保证已成为制约网格应用的瓶颈之一.如何建立一个开放的、可扩展的体系结构,是当前支持端到端服务质量的服务网格体系结构研究的重要问题.提出了支持服务质量的服务网格层次体系结构(QESA),并通过对网格服务容器、信息服务与调度服务的服务质量扩展实现了该体系结构,设计了基于资源能力管理与服务预留的服务质量保证方法,讨论了服务质量感知的服务发现和服务调度的实现机制.通过中尺度天气系统降水量预报的网格应用(AREM)对其进行了性能评价,结果表明,基于QESA的服务网格中间件可为网格作业提供确定的服务质量保证能力.     

基于SOA的网格安全技术研究

随着网格技术的不断发展以及对网格研究的不断深入,对网格安全的需求不提高,面向服务的体系结构研究成果为分布式、可扩展性、可跨域管理以及软件的重用与集成提供了一个最佳的解决方案。本文将网格所涉及的安全需求做成服务的形式,设计了一个面向服务的网格安全体系结构,并以网格认证服务为实例,探讨了网格安全服务的设计与重用,它集成了多种常用的认证技术,实现网格安全服务的跨域互操作。     

基于Web服务的网格化智能Agent传感器研究

网格智能化测控是测控技术的一个新的发展方向,传感器作为网格测控系统的一个独立节点,具有网格和某种智能功能是必要的;网格化技术可以实现网络传感器节点的自主管理,分布式计算、测试,以及对测试数据的智能化处理,但如何实现网络传感器的网格化是一大技术难题;文章在ARM9微处理器为核心的硬件环境下,基于嵌入式Web服务技术,采用智能Agent技术和嵌入式Web服务开发工具gSoap实现了网络传感器的智能化和网格功能,并给出了系统性能的测试结果。     

面向网格服务的标准件库系统集成

基于开放网格服务体系结构提出了面向服务的标准件库系统集成的体系结构．将标准件库系统中与数据库、CAD系统交互的功能组件封装在网格服务容器中,并与后台数据库一起部署成为网格服务节点,现有的标准件库系统只需提供服务的行为接口即可方便地集成到网格环境中．开发部署了一类标准件库网格服务节点,验证了该体系结构和实现技术的有效性．     

A Decentralized Computational Infrastructure for Grid-Based Parallel Asynchronous Iterative Applications

Parallel asynchronous iterative algorithms relax synchronization and communication requirements, and can potentially extend Desktop Grids beyond embarrassingly parallel applications to support a broader class of parallel iterative applications. This paper presents the design and implementation of CometG, a decentralized (peer-to-peer) computational infrastructure that extends Desktop Grid environments to support these applications. CometG provides a decentralized and scalable tuple space, efficient communication and coordination support, and application-level abstractions that can be used to implement Desktop Grid applications based on parallel asynchronous iterative algorithms using the master-worker/BOT paradigm. The deployment and evaluations of CometG and a CometG-based application in a wide-area environment using the PlanetLab [7] test bed, as well as a campus network are presented.     

Performance Driven WS Orchestration and Deployment in Service Oriented Infrastructure

Composite Web services (WS) can be seen as software systems designed according to workflow-based orchestration of building blocks or simpler WS. Each block has its own specifications concerning both functional and non-functional properties. While the characteristics of each block have a scope limited to its domain, the WS must guarantee service levels that are usually described by global end-to-end metrics. The problem of relating local to global objectives in WS orchestration is hard to approach. In this context, some WS components have to be deployed in distributed service oriented infrastructure mixing heterogeneous systems belonging to private and/or public providers. In this paper we propose a performance-driven technique for designing and deploying composite WS on heterogeneous service oriented infrastructure. Users having different requirements in terms of resource demands and performance objectives are considered. Several WS deployment alternatives, involving both physical and virtual resources provided by the infrastructure, are evaluated to identify the logical (workflow) and physical (deployment) configuration allowing to meet the requirements. In order to demonstrate the suitability of the proposed approach to the service oriented context, an example of a travel management WS is described and the optimal deployment of the components in a hybrid infrastructure is investigated.     

Intercontinental Grids: An Infrastructure for Demand-Driven Innovation

This paper charts the evolution of an intercontinental Grid—INWA—from its first operation connecting Australia and Scotland; its subsequent extension to China; and its use to demonstrate the first large-scale research and education network for the Asia-Pacific region. The paper focuses on the gap between e-Science and e-Social Science arguing that the Grid topology is more compatible with the socio-legal demands of large-scale study of society than more dynamically distributed approaches, such as Cloud Computing. Foundational texts on Grid Computing and its appropriation by research programmes in the UK, USA and China have helped create a positive, symbolic value for Grid Computing. For INWA, this value helped when communicating the aims of the project to potential collaborators and so created the conditions for high-quality, socio-economic data to be placed in a collaborative, analytical environment. There is no equivalent symbolic value for Cloud Computing with potential consequences for its usefulness in establishing such collaborations in future.     

面向服务的织女星网格系统软件设计与评测

网格是开放的分布式系统,具有自治、动态和可扩展特性．在Internet环境下实现网格系统必须解决大规模资源共享与协同问题,也就是如何将Internet上无序的资源有序组织的问题．织女星网格系统软件针对现有网格平台软件存在的不足,借鉴传统计算机系统结构的方法来研究网格体系结构及其系统软件．面向网格应用的共性需求,提出了面向服务的层次化软件结构;引入网格资源空间的概念,实现了网格资源的虚拟化,屏蔽使用网格资源的技术细节．文章通过对网格关键问题的讨论,阐述了织女星网格系统软件的关键技术和设计思路,并通过对传统批作业的测试,分析了织女星网格系统软件的性能．     

Grid Infrastructure Monitoring Service Framework Jiro/JMX Based Implementation

The paper describes a grid infrastructure monitoring service based on Jiro and JMX. Involvement of those technologies gives the programmer ease of instrumentation, dynamic configuration and simple to use discovery and notification mechanisms. Moreover, building the system over existing standards accepted by the IT industry makes this process stable in longer period of time. The goals of the autors of the service's concept were not only to provide the user with yet another front-end for SNMP, but also to let the system resolve typical problems by involving existing or forthcoming technologies supporting declarative way of programming. Being structured as a framework, the system allows the user to describe rules that define the actions taken by the system and conditions, upon which the actions should be taken. The system is currently developed further by the Distributed Systems Research Group at the University of Mining and Metallurgy in Kraków.     

网格环境下一种可扩展的资源发现机制

在分布、异构的网格环境下,如何快速、准确地查找用户所需要的资源是影响网格计算性能的重要因素。本文针对集中式资源发现方法存在的可扩展性弱的不足,将P2P方法应用到网格资源发现领域,提出了一种扩展性好的分布式资源发现方法。该方法使用二叉树来管理数据,网格中每个节点都负责管理一部分资源信息。实验结果表明,本文提
出的方法能有效解决集中式资源发现方法可扩展性不好、资源信息服务器负载过重、容易造成单点失效等问题。     

Privacy-Enhancing Decentralized Anonymous Credential in Smart Grids

Decentralized Anonymous Credential (DAC) has posed enormous potential in smart grids for protecting user privacy (e.g. preventing user’s daily life from being sketched out). However, the existing DAC protocols still compromise user privacy for a full list of attributes are disclosed during showing credentials. In this paper, to construct a privacy-enhancing decentralized anonymous credential (PEDAC) protocol, we first design a more efficient range proof to hide user’s attributes. Specifically, we are inspired by Camenisch et al. (ASIACRYPT 2008), but replace their adopted Boneh-Boyen signature scheme with the Chinese standard SM2 signature scheme (incorporated in the ISO/IEC 14888-3) to propose pairing-free set membership and range proof protocols. These protocols can be executed non-interactively upon the Fiat-Shamir heuristic (INDOCRYPT 2012), and then be used to construct our PEDAC protocol. By compared with the protocols of Camenisch et al. (ASIACRYPT 2008) and Poelstra et al. (FC 2018), our proposed range proofs are with less communication and computation costs and hence more practical for constructing PEDAC protocols in smart grids.     

一种基于角色的分布式动态服务组合方法

服务组合是开放环境中实现跨组织敏捷应用集成的重要技术.许多研究采用集中的服务组合引擎管理组合服务的执行,在系统的可伸缩性、消息传输效率及自治性等方面存在局限.针对集中结构的上述问题,提出一种基于角色的分布式动态服务组合方法,通过划分组合服务的全局流程模型产生各个角色的本地流程模型,从而使得组合服务的控制逻辑及执行负载能够对等地分布到多个结点.讨论了本地流程模型的生成算法及部署与执行机制.模拟实验结果表明,与集中式结构相比,该方法能够更有效地支持大规模并发访问以及大数据量的消息转输,有助于提高组合服务的可伸缩性.     

面向信息服务的网格资源管理器的设计

设计一个面向信息服务的网格资源管理器的架构，该架构分为全局和局部管理器。介绍一个新的作业调度算法，该算法的特点是根据历史作业执行时间来预测当前作业的执行时间，在调度时考虑作业执行时间和截止时间2个要素。试验证明该算法比目前常用的Max-Min和Min-Min算法具有更好的性能。     

Validation of Grid Middleware for the European Grid Infrastructure

The European Grid Infrastructure (EGI) is providing a sustainable pan–European Computing Grid to support e–Science, integrating more than 350 computing resource centers worldwide. One of its main challenges is that the middleware driving this production infrastructure is constantly evolving, as it adapts to the changing needs of the EGI Community. Since the software is provided by external technology providers, it needs to pass through a quality verification process before it is included in the EGI official release called Unified Middleware Distribution (UMD). Therefore, all software components undergo a release process covering the definition of the functionality and quality criteria, the verification of those criteria, and the testing under production environments. This paper details the design, development and implementation of this software validation process. An analysis is performed on several metrics to evaluate the process impact on the stability of the production infrastructure, by capturing malfunctions and other issues at the initial testing phases.