支持组合服务QoS动态优化的服务总线

面向服务的体系结构SOA已经逐渐成为应用软件系统集成的主流技术。服务总线在构建SOA基础架构中起着关键作用,如何根据服务QoS进行动态优化是服务总线中的重要研究课题之一。SOARBus是一个支持QoS动态优化的服务总线,SOARBus实现组合服务请求动态调度算法和QoS感知的组合服务动态调整算法,使其能够根据引擎负载按照负载均衡原则对组合服务请求进行动态调度和以及在组合服务执行期间根据QoS对组合服务进行动态调整。     

一种基于SOA的企业集成平台

提出一种基于SOA的企业集成平台——JSSOA,以企业服务集成中间件为核心,实现异构系统和多种类型服务的透明集成,支持基于MDA方法面向最终用户的流程建模和服务组合、基于语义及QoS的服务查找、基于服务的个性化应用系统用户界面创制。该平台封装了复杂的SOA技术细节,使基于SOA的应用系统的构建、运行和维护更简单、高效。     

面向服务遥感图像处理平台中时间感知的服务质量预测

面向服务架构(SOA)通过将遥感图像处理算法抽象成组件化的服务，进一步通过服务选择及组合，满足遥感图像处理的复杂业务需求。为了得到满足用户服务质量(QoS)要求的服务组件进行组合，前提就是获得所有服务的QoS。然而，对于用户未调用过的服务，其QoS是缺失的，因此围绕缺失QoS的预测出现了很多研究工作。针对目前QoS预测没有考虑时效性，进而影响了QoS预测准确度的问题,通过考虑时效性提出基于时间片的QoS模型，进一步基于协同过滤提出时间感知的QoS预测方法。在WS-DREAM真实数据集中的实验结果表明，时间感知的QoS预测方法能够获得较小的均方误差(MAE)和均方根误差(RMSE)。此外，对于可能影响时间感知QoS预测的多个参数，通过设置不同的参数组合进行了多次实验和分析，为参数的选择提供了一定的参考。     

随机QoS 感知的可靠Web 服务组合

在面向服务的环境下,单个Web 服务往往不能满足用户的要求,这时就需将已有的单个Web 服务进行组合,以便产生满足用户需求的、增值的组合服务.已有的服务组合方法都很少考虑Web 服务的随机性和Internet 环境的动态性,从而在服务选择过程中产生的规划都是静态规划,结果导致在服务组合时都以较大概率出现组合失败.针对上述问题,提出了Web 服务各随机QoS 指标的度量方法和自适应QoS 管理体系结构,并利用随机型离散事件系统唯一的动态控制方法——马尔可夫决策过程(MDP),设计出随机QoS 感知的可靠Web 服务组合算法.实验结果表明,考虑随机性的QoS 度量方法和QoS 管理体系结构,以及平衡了“风险”与“报酬”的MDP 有效地提高了服务组合成功率.     

面向SOA关键型系统的混合关键度驱动自适应资源管理

针对运行于开放、不确定环境下的SOA架构的多使命复杂关键型系统,提出了一种以混合关键度为驱动的动态分级自适应资源分配算法。它通过构造闭环反馈的分布式控制环,在线动态调整任务Qos,针对不同关键度的任务动态调整资源分配。该方法不但在统计意义上确保了关键型系统的实时性,而且实验证明该方法能有效提高系统在高负载条件下的实际资源利用率和降低关键任务的死线错过率,保证了关键型系统的高可靠性。     

基于改进磷虾群算法的服务组合优化

面向服务的架构（SOA）下,针对服务组合优化过程中易陷入局部最优、时间开销大的问题,提出一种加入自适应交叉算子和随机扰动算子的改进磷虾群算法PRKH。首先基于服务质量（QoS）建立了服务组合优化模型,并给出不同结构下QoS的计算公式和归一化处理方法。然后在磷虾群（KH）算法的基础上加入自适应的交叉概率和基于实际偏移量的随机扰动,从而在磷虾群的全局搜索能力和局部搜索能力之间达到良好平衡。最后通过仿真,把所提算法与KH算法、粒子群优化（PSO）算法、人工蜂群（ABC）算法和花朵授粉算法（FPA）进行对比,实验结果表明,PRKH算法能够更快找到QoS更优的复合服务。     

SOA架构在Web扩展服务的探讨

本文探讨了面向服务的体系结构(SOA)架构和Web服务,SOA可以基于Web服务,也可以将Web服务的使用从简单的客户端-服务器模型扩展成任意复杂的系统,对Web服务进行扩展.最后以一家金融业公司通过SOA简化借贷业务系统来说明SOA在Web扩展服务的应用.     

基于二维QoS模型的Web服务组合

在实际应用中,单个Web服务通常无法满足复杂应用的需求,如何组合已有的服务,从而提供更强大更完整的商业功能已成为此领域的研究热点。然而现行的SOA架构中,Web服务组合方法中很少考虑Web服务质量（QoS）问题,或者对Qos考虑得不够全面,这样,组合出的服务不能确保能够满足用户的QoS需求。针对这一问题,提出了Web服务的二维QoS模型,并使用了改进的UDDI规范,在此基础上给出了基于QoS的Web服务组合的有色Petri网组合策略。在满足用户组合服务的功能需求的同时,也满足了用户对服务质量QoS的需求,实现了需求服务的优化。     

一种工作流环境下能耗感知的多路径服务组合方法

当前,服务组合方法只考虑组合服务QoS的优化而不考虑组合服务的能耗优化.针对这一问题,文中首先根据不同情况提出了两种服务能耗模型;其次在基于工作流的服务组合环境下,提出了一种能耗感知的多路径服务组合方法 EAMSC.该方法对服务组合的能耗优化问题进行了数学建模,并提出了一种基于启发式的多路径服务组合算法,该算法包括两个部分:一是组合服务的可行路径查找,即在满足端到端QoS约束的前提下找出若干条可行的服务组合路径;二是请求速率的分配,即在可行的服务组合路径上依据服务能耗模型分配请求流量以降低组合服务的总体能耗.最后,仿真实验结果表明:能耗感知的多路径服务组合方法与传统的服务组合方法相比,能够在保证端到端QoS约束的基础上有效地减少组合服务的总能耗.     

基于用户请求服务的QoS评价模型

进行SOA系统构建时,在选择同一功能服务不同物理实现的过程中,需要考虑用户适合度。提出根据用户需求确定服务QoS属性集的方法,该方法用扩展的WSDL协议描述服务QoS,量化服务QoS和用户QoS需求。构建基于用户请求的服务质量模型和相应算法,完成对最佳用户适合度服务物理实现的选择。     

QoS驱动的服务动态替换方法

在基于SOA(Service-Oriented Architecture)的软件中,为了适应用户对软件QoS(Quality of Service)值要求的改变或是组成软件的Web服务本身QoS值的不稳定,需要对软件进行重配置,使其QoS值达到用户要求。提出一个QoS驱动的动态替换算法,通过对软件的QoS的监测结果或用户所提出的QoS需求,确定动态替换目标。通过目标的替换,使配置后的软件满足用户需求。理论分析和实验结果都说明了算法的可行性和有效性。     

GOS: a global optimal selection strategies for QoS-aware web services composition

Services composition technology provides a promising way to create new services in services-oriented architecture. However, some challenges are hindering the application of services composition. One of the major challenges encountered by composite services developer is how to effectively select a set of services across different autonomous regions (e.g., organization or business) to instantiate a composite service which can satisfy user’s QoS constraints. To solve QoS-aware Web service composition problem, this paper proposes a global optimization selection (GOS) approach based on prediction mechanism for QoS values of local services. The GOS includes two parts. First, the local preprocessing service selection algorithm can be used to increase composite services performance in run-time by predicting the change of service quality parameters. Second, GOS aims at enhancing the run-time performance of global selection by reducing QoS aggregation operations. The simulation results show that the GOS has excellent selection and lower execution cost than existing approaches.     

Broker-based SLA-aware composite service provisioning

QoS-aware service composition aims to satisfy users’ quality of services (QoS) needs during service composition. Traditional methods simply attempt to maximize user satisfaction by provisioning the composite service instance with the best QoS. These “best-effort” methods fail to take into account that there also exist other consumers competing for the service resources and their decisions of service selection/composition can impact on QoS. Since user's QoS needs can be met once the demanded level is reached, in this paper, we propose an “on-demand” strategy for QoS-aware service composition to replace the traditional “best-effort” strategy. The service broker is introduced to facilitate implementation of this strategy: it first purchases a number of service instances for each component from providers and then provisions the composite services with different QoS classes to consumers. This paper focuses on how the broker follows the service level agreement (SLA) to provision composite services in the “on-demand” manner. This problem is formally expressed as the minimization of the QoS distance function between SLA and QoS of composite service instances, under a series of constraints. Heuristic approaches are proposed for the problem and experiments are conducted at last to verify their effectiveness and efficiency.     

支持QoS的Web服务选择模型的研究与实现

提出一种新的支持服务质量(QoS)的Web服务选择模型(WSSM-Q)。该模型定义了一组描述Web服务QoS指标的分类tModel,用QoS量化值描述服务提供者的QoS通告,用约束型需求和偏好型需求描述服务消费者的QoS需求,采用四阶段选择算法选择满足消费者需求的Web服务。实验结果表明该模型是可行的和有效的。     

基于FAHP与规划图融合的Web服务组合方法

近年来,随着云计算的发展,越来越多的服务被发布在网上。如何将不同的Web服务组合在一起并使其满足功能性需求和非功能性需求成为了一个研究难点。Web服务质量(Quality of Service,QoS)感知的Web服务组合问题属于NP难问题。为了解决这个问题,文中提出一种融合FAHP与改进Graphp lan算法的方法(FAHP and Improved Graphplan,FIGP)。首先,根据用户偏好使用模糊分析层生成服务的综合QoS;其次,在Graphplan向前扩展中,使用动态阈值对竞争力较差的服务进行剪枝,在保留关键服务的同时降低了时间复杂度;最后,在Graphplan向后搜索阶段,在满足功能性需求的前提下选择综合QoS最好的服务加入到组合中。实例分析和实验结果表明,与普通的Graphplan,Skyline及其他方法相比,FIGP不仅较好地提高了服务组合的质量,而且显著缩短了程序的执行时间。     

An adaptive algorithm for QoS-aware service composition in grid environments

Service composition enables users to realize their complex needs as a single request and it has been recognized as a flexible way for resource sharing and application integration since the appearance of Service-Oriented Architecture (SOA). For each of the needed individual services there may be many candidate services available presented by different vendors and with different functional and non-functional properties such as Quality of Service (QoS). Approaches are needed to select candidate services with various QoS levels according to user’s performance requirements meanwhile adapt to dynamic churn in grid environments. This paper mainly focuses on adaptive management of QoS-aware service composition in grid environments and proposes an adaptive algorithm for QoS-aware service composition (AQSC). In AQSC we model this problem as the Multi-Constrained Optimal Path selection problem (MCOP) and use heuristic approach for service selection, then backup services set is introduced as an adaptive mechanism so as to ensure the fulfillment of composite service when some candidate services fail or withdraw. Both theoretical analysis and simulation results indicate that AQSC has high composition success rate, finish rate and low cost.     

QoS全局最优的多目标Web服务选择算法*

针对现有方法的不足,提出一种基于QoS全局最优的多目标动态Web服务选择算法。在给出动态服务组合模型的基础上,以“抽象服务规划”为输入,以用户的非功能性需求为全局约束,将动态服务选择问题转换为一个带QoS约束的多目标服务组合优化问题;利用多目标蚁群算法,多个目标函数被同时优化并产生一组满足约束条件的Pareto优化解。通过运用实验与基于多目标遗传算法的Web服务选择算法进行对比,证明了该方法的可行性和有效性。     

A novel heuristic algorithm for QoS-aware end-to-end service composition

Many works have been carried out to find the efficient algorithms for QoS-aware service composition in recent years. Nevertheless, on one hand, some of these works only consider the local QoS attributes in Web services composition; on the other hand, some ideas derived from QoS selection algorithms for network routing are directly applied in service composition without any adaption. A service composition model with end-to-end QoS constraints has been presented in this paper. An improved heuristics HCE based on the observation of characteristic of end-to-end service composition is proposed as a novel solution. Simulation results reveal the better performance of proposed heuristic compared to the other two heuristics, HMCOP and generic CE algorithm.     

QoS-aware service composition for distributed video surveillance

Quality of Service (QoS) is essential for the ubiquitous access of media services in real-time distributed video surveillance applications. To have ubiquitous access of desired media with emergency officials’ handheld devices, appropriate media transcoding services are required. Currently, it is challenging to select and compose these services for each of the devices to satisfy the desired QoS demand. To compose these media services so that video stream is available for target pervasive and smart devices, a composition algorithm is required. Thus, this paper presents a QoS-aware service composition algorithm to select the best composition for the target ubiquitous client so that it can optimally provide QoS to heterogeneous users. We have implemented a video surveillance prototype to demonstrate the performance of the proposed QoS-aware composition algorithm. Results from this prototype reveal that the approach is suitable for real-time video surveillance.