面向制造任务的云制造虚拟车间构造方法

针对云制造模式下快速选择和组织相关制造资源、保证制造任务执行的问题,提出一种面向制造任务的云制造虚拟车间构造方法。该方法将制造过程抽象为制造任务执行链,链中的节点对应制造设备云服务或检验云服务,链中的有向边对应物流云服务;并通过行业域、地域和类型域来组织管理云服务,以构造规模较小的候选云服务集,同时减少功能匹配、性能匹配、价格匹配和时间匹配的计算量,达到快速构建云制造虚拟车间的目的。算例分析表明,相比其他方法,该方法能够在更短的时间内完成云服务的选择,并保证所选云服务的服务质量（QoS）在相关域中是更好的。     

基于业务流程的制造云服务组合模型

为了提高云制造系统中制造云服务的组合成功率,实现组合云服务与用户业务需求的准确匹配,在对制造云服务、流程节点任务、云服务的可组合性和流程匹配进行形式化描述的基础上,提出一种基于业务流程的制造云服务组合模型。该模型由业务流程引擎、业务流程、选择逻辑、评估逻辑、监控逻辑、知识库和原子云服务集构成,在功能匹配的基础上,对候选服务的可组合性进行检查,结合负载、服务质量(QoS)和业务流程信息,选择合适的云服务,并将其挂接在业务流程上实现制造云服务的组合。对制造云服务的组合流程进行了详细描述,并给出云服务组合的实现方法。实例分析表明,该模型能够有效地选择满足业务需求的云服务实体并进行组合,从而提高制造云服务的组合成功率,保障用户制造活动的顺利进行。     

考虑执行可靠性的云制造服务组合算法

由于制造资源的调用与执行比计算资源要复杂得多,使得在云制造环境下的服务组合执行可靠性成为必须考虑的问题.为此,提出一种基于离散粒子群智能优化的、考虑执行可靠性的云制造服务组合算法.以概率密度函数描述服务可靠性,基于服务模型库动态生成云制造服务组合的工作流模型,基于语义实现服务匹配,通过离散变量粒子群优化算法计算出执行可靠性最优的云制造服务组合方案.最后以结构设计工作流模型为例,在不同服务实例规模、不同恶意服务占比情况下验证了其有效性和可靠性.实例结果表明,在恶意服务占比较高时,该算法仍能保持较高的服务执行可靠性.     

一种基于反馈控制的Web服务组合执行引擎设计

在Web服务组合执行引擎中解耦流程执行和成分Web服务调用,设计和实施了带有双控制反馈控制环的流程执行结构,反馈控制环分别位于流程执行器与服务代理之上。仿真结果表明：解耦流程执行和成分Web服务调用提高了引擎资源的使用效率,增加了流程执行的并发性,提高了引擎的吞吐量;引入QoS反馈控制结构,使得引擎在组合服务负荷变化时,可为不同的请求服务等级提供服务响应时间保障。     

基于QoS的自适应控制中间件研究与应用

文章重点研究在自适应控制中间件支持下,Web服务组合执行引擎的QoS管理机制,设计了一个基于QoS的自适应控制中间件,并应用于Web服务组合执行引擎当中,以支持对服务请求的分级处理,实现了为不同等级用户提供区分服务的功能,为提高可变负载下单个执行引擎的高吞吐量和快速响应时间提供了一种有效的解决方案。     

Web服务组合执行引擎中服务代理运行机制研究

在Web服务组合执行引擎WebJetFlow中解耦流程执行和成分Web服务调用,将服务代理的服务调用由同步模式转变为单纯异步模式,并用NS2模拟器针对服务代理的同步模式转变为单纯异步模式,以及有服务代理和无服务代理的两种不同的引擎处理机制分别进行模拟仿真。仿真结果证明：在同样的线程资源条件下,有服务代理的引擎访问流量大于无服务代理引擎;解耦流程执行和成分Web服务调用以及单纯异步调用模式提高了引擎资源的使用效率、增加了流程执行的并发性、改善了引擎的吞吐量和性能。     

Web服务组合事务处理研究与实现

通过重用已有的服务进行服务组合来实现应用集成;而保证服务组合的事务特性是实现服务组合的关键。文中提出一个Web服务组合事务处理模型,将BPEL (Business Process Execution Language,业务流程执行语言)的流程设计与WS-C/T (Web Services Coordination/Transaction,Web服务协调/事务)规范结合。该模型主要由客户端、BPEL执行引擎、事务协调器和参与者四个部分组成。客户端发起请求,BPEL执行引擎响应请求并开启事务,事务协调器和参与者根据事务协调算法完成事务协调。     

Web服务组合事务处理研究与实现

通过重用已有的服务进行服务组合来实现应用集成;而保证服务组合的事务特性是实现服务组合的关键。文中提出一个Web服务组合事务处理模型,将BPEL（Business Process Execution Language,业务流程执行语言）的流程设计与WS—C／T（Web Services Coordination/Transaction, Web服务协调／事务）规范结合。该模型主要由客户端、BPEL执行引擎、事务协调器和参与者四个部分组成。客户端发起请求,BPEL执行引擎响应请求并开启事务,事务协调器和参与者根据事务协调算法完成事务协调。     

基于反馈控制的服务组合引擎的设计与实现

遵循SOA,提出服务组和执行引擎WebJetFlow的实现框架。将反馈控制机制应用于执行引擎中,在流程执行管理器和服务代理中,设计带有反馈控制环的流程执行结构,以保障不同等级的服务请求的服务响应时间。在执行模块中,将流程执行与对服务的调用进行分离,提高了引擎资源的利用率。解耦流程执行和Web服务调用提高了引擎资源的使用效率。QoS反馈控制结构使得引擎在外部请求负荷变化时,可为不同等级的请求提供服务响应时间保障。     

Apache ODE环境下Web服务组合技术的研究

BPE以业务流程执行语言)是一门用于自动化业务流程的形式规约语言,它对Web服务组合进行描述,而ApacheODE执行引擎负责BPEL定义的解析和执行,为BPEL流程提供运行环境,但是Apache ODE引擎部署和执行BPEL流程还需要各种服务的WSDL描述、组合后的服务的WSDL描述以及流程部署描述文件,Apache ODE并不提供工具为完成这些功能.通过对Apache ODE结构以及部署、执行BPEL流程的原理进行分析,设计算法自动生成部署描述文件和服务的WSDL描述等,从而完成Apache ODE引擎环境下服务组合的自动化部署和执行.     

自组织网络有效的组合服务执行路径发现方法

无线自组织网络中的服务组合是指通过将几个简单的服务即原子服务组合成一个功能更强大的服务,来满足用户提出的复杂的请求。在无线自组织网络中,组合服务的执行首先要找到能够实现服务组合的执行路径,即确定网络中能够实现组合服务的合成方案及提供各原子服务的节点。已有工作提出的服务组合执行路径的发现方法并没有考虑所发现执行路径需要的开销和服务的执行情况。文章在保证组合服务执行路径发现成功率的前提下,提出了两种限制跳数的组合服务执行路径发现方法,通过限制组合服务执行路径请求包广播的跳数来减少网络中请求包转发的数量,避免无用的传输消耗。实验证明提出的方法有效地减少了网络中执行路径请求包的转发量,降低了网络的负载。     

An experience report on developing an automated web services platform

Web services have attracted significant industry interest as a low-cost and flexible technology alternative to distributed object and proprietary message-oriented methods for delivery of on-demand business processes, enabling intra-organizational systems integration, and in the long term, development of dynamic inter-organizational process networks that may revolutionize B2C and B2B e-commerce. Exploiting this latent potential of web services technology requires the development of automated techniques for scalable and reliable service composition and execution in web service platforms. In this paper, we summarize our experience in developing an architectural framework for web services platforms, called Integrated Service Planning and Execution architecture (ISP & E). The use of recent advances in AI planning, learning and semantic web technologies for service composition, reliable service execution, transaction synthesis, and model-driven deployment of services is discussed. Furthermore, we discuss implications for and research issues in the development of web services based systems to aid e-business.     

Towards IoT-enabled dynamic service optimal selection in multiple manufacturing clouds

With the Internet of Things, it is now possible to sense the real-time status of manufacturing objects and processes. For complex Service Selection (SS) in Cloud Manufacturing, real-time information can be utilized to deal with uncertainties emerging during task execution. Moreover, in the face of diversified demands, multiple manufacturing clouds (MCs) can provide a much wider range of choices of services with their real-time status. However, most researchers have neglected the superiority of multiple MCs and failed to make a study of how to utilize the abundant and diverse resources of multiple MCs, let alone the multi-MCs service mode under dynamic environment. Therefore, we first propose a new dynamic SS paradigm that can leverage the abundant services from multiple MCs, real-time sensing ability of the Internet of Things (IoT) and big data analytics technology for knowledge and insights. In this way, providing optimal manufacturing services (with high QoS) for customers can be guaranteed under dynamic environments. In addition, considering that a relatively long time might be spent to complete a complex manufacturing task after SS, a quantified approach, based on the Analytic Hierarchy Process and big data, is proposed to evaluate whether the intended cloud manufacturing services should be reserved to make sure that eligible services are ready to use without compromising cost or time. In this paper, the problem of IoT-enabled dynamic SS across multiple MCs is formulated in detail to enable an event-driven adaptive scheduling when the model is faced with three kinds of uncertainties (of the service market, service execution and the user side respectively). Experiments with different settings are also performed, which show the advantages of our proposed paradigm and optimization model.     

基于自适应粒子群算法的制造云服务组合研究

针对云制造系统中制造云服务组合的多目标规划问题,研究建立了问题模型并提出了求解方法。首先引入了网格制造模式的制造资源服务组合技术,探讨并描述了云制造模式中基于服务质量（QoS）的制造云服务组合过程;接着通过分析云制造模式下制造云服务的特征并基于制造领域知识,研究定义了制造云服务的八维QoS评估标准及计算表达式,推导出制造组合云服务的QoS表达,进而建立了制造云服务组合的多目标规划问题模型。最终设计了自适应粒子群算法来解决该多目标规划问题。仿真实验表明,该算法能有效并高效地解决该问题,且求解效率优于传统粒子群算法。     

基于LG-MMAS算法的制造云服务优化组合研究

制造云服务组合是一种提高云制造资源利用率,实现制造资源增值的新技术,对云制造产业的快速发展具有重要的支撑作用。随着云制造技术的日益成熟,网络上出现了大量具有相同制造功能和不同服务质量的制造云服务,如何通过这些制造云服务构建出既能满足用户制造需求,又具有最优服务质量的组合服务是云制造领域面临的难题。针对这一问题,将协作学习、变异和精英保留机制引入最大最小蚁群算法,构造了具有学习和变异能力的最大最小蚁群算法,并使用该算法求解服务质量感知的制造云服务优化组合问题。仿真实验结果验证了算法的有效性。     

多目标事务模糊关联聚类的云制造服务组合算法

目前的云制造服务组合方法单纯从某个角度研究服务组合问题,对基于多目标事务的云制造服务组合的考虑不足,服务组合质量不高。为实现敏捷、智能、平稳的云制造服务组合,基于开展多目标事务的云模式通用解析、多目标事务模糊关联特征的云模式通用表示、云制造服务组合多目标事务模糊关联聚类算法等方面研究,改进反向学习算法、可替换服务推荐算法、三角模糊函数、非支配排序遗传公式,设计一种敏捷、智能、平稳的云制造服务组合算法。最后,实施实验验证,与传统算法进行性能对比分析。实验结果表明,相比传统算法,该算法组合响应时间短、误差小,且收敛性、敏捷性、智能性、动态演化性、平稳性高。因此,该算法实现了基于多目标事务模糊关联聚类的云制造服务的有效组合,具有较高的应用价值。     

An effective dynamic service composition reconfiguration approach when service exceptions occur in real-life cloud manufacturing

Cloud Manufacturing Service Composition (CMSC), as one of the key issues of Cloud Manufacturing (CMfg), has already attracted much attention. Existing researches on CMSC mainly focus on the optimization efficiency in ideal conditions, while scarcely focus on how to efficiently reconfigure CMSC when service exceptions occur. Uncertain service exceptions often occur during CMSC's execution in real-life CMfg. Thus, it is an urgent issue to perform an adjustment for CMSC to continue to complete the processing task. Besides, some practical constraints are non-negligible in real-world CMfg. Thus, it is necessary to consider them when reconfiguring CMSC. To bridge these gaps, this paper proposes a dynamic service composition reconfiguration model when service exceptions occur under practical constraints (DSCRWECPC). This model redefines optimization objectives, including machining quality, service quality, and cost. Besides, DSCRWECPC considers service exceptions, the cloud manufacturing service occupancy time constraint, the strict time constraint of original CMSC, and dynamic service quality change as its practical constraints. To solve this model, this paper proposes a service composition reconfiguration algorithm (SCRIHHO) based on the strengthened Harris Hawks Optimizer (HHO). Finally, to certify SCRIHHO's performance, this paper conducts numerical experiments and the case application to perform comparisons between SCRIHHO and other algorithms (Particle Swarm Optimization (PSO) and Grey Wolf Optimizer (GWO)). Results showed SCRIHHO in this paper is superior to PSO, GWO when tackling the practical DSCRWECPC in CMfg.     

Hybrid Chameleon and Honey Badger Optimization Algorithm for QoS-Based Cloud Service Composition Problem

Cloud computing facilitates the great potentiality of storing and managing remote access to services in terms of software as a service (SaaS). Several organizations have moved towards outsourcing over the cloud to reduce the burden on local resources. In this context, the metaheuristic optimization method is determined to be highly suitable for selecting appropriate services that comply with the requirements of the client’s requests, as the services stored over the cloud are too complex and scalable. To achieve better service composition, the parameters of Quality of Service (QoS) related to each service considered to be the best resource need to be selected and optimized for attaining potential services over the cloud. Thus, the cloud service composition needs to concentrate on the selection and integration of services over the cloud to satisfy the client’s requests. In this paper, a Hybrid Chameleon and Honey Badger Optimization Algorithm (HCHBOA)-based cloud service composition scheme is presented for achieving efficient services with satisfying the requirements of QoS over the cloud. This proposed HCHBOA integrated the merits of the Chameleon Search Algorithm (CSA) and Honey Badger Optimization Algorithm (HBOA) for balancing the trade-off between the rate of exploration and exploitation. It specifically used HBOA for tuning the parameters of CSA automatically so that CSA could adapt its performance depending on its incorporated tuning factors. The experimental results of the proposed HCHBOA with experimental datasets exhibited its predominance by improving the response time by 21.38%, availability by 20.93% and reliability by 19.31% with a minimized execution time of 23.18%, compared to the baseline cloud service composition schemes used for investigation.