Short-term performance management by priority-based queueing

Service-based IT infrastructures serve many different business processes on a shared infrastructure in parallel. The automated request execution on the interconnected software components, hosted on heterogeneous hardware resources, is typically orchestrated by distributed transaction processing (DTP) systems. While pre-defined quality-of-service metrics must be met, IT providers have to deal with short-term demand fluctuations. Adaptive prioritization is a way to react to short-term demand variances. Performance modeling can be applied to predict the impact of prioritization on the overall performance of the system. In this paper, we describe the workload characteristics and particularities of two real-world DTP systems and evaluate the effects of prioritization regarding overall load and end-to-end performance measures.     

信息技术服务的业务模式研究

信息技术（IT）服务企业所采用的业务模式不仅直接影响着信息技术服务提供和传递的质量,而且对整个IT服务行业未来的发展模式也将产生重要影响。分析了信息技术服务的内涵,指出IT服务具有生产性服务的特征;在此基础上,分别按照服务需求的分离点和IT服务的实现方式,对IT服务企业的业务模式进行了分类研究;并对IT服务业中面向产品、面向服务和租赁的3种业务模式及其特征进行了分析,为促进IT服务业的快速发展提供基础。     

Model-based services convergence and multi-clouds integration

With the development of cloud computing, IT users (individuals, enterprises and even public services providers) are transferring their jobs or businesses to public online services provided by professional information service companies. These information service companies provide applications as public resources to support the business operation of their customers. However, no cloud computing service vendor (CCSV) can satisfy the full functional information system requirements of its customers. As a result, its customers often have to simultaneously use services distributed in different clouds and do some connectivity jobs manually. Services convergence and multi-clouds integration will lead to new business models and trigger new integration technologies that provide solutions to satisfy IT users’ complicated requirements. This paper firstly reviews the development of cloud computing from business and technical viewpoints and then discusses requirements and challenges of services convergence and multi-clouds integrations. Thirdly, a model based architecture of multi-clouds integration is provided. Business logic modelling for cross-organizational collaboration, service modelling and operation modelling methods with relative model mapping technology are discussed in detail. Some key enabling technologies are also developed. At last, case studies are presented to illustrate the implementation of the technologies developed in the paper.     

Exploring gate-limited analytical models for high-performance network storage servers

Gate-limited service is a type of service discipline found in queueing theory and can be used to describe a number of operational environments, for example, large transport systems such as buses, trains or taxis, etc. Recently, there has been the observation that such systems can also be used to describe interactive Internet Services which use a Client/Server interaction. In addition, new services of this genre are being developed for the local area. One such service is a Network Memory Server (NMS) being developed here at Middlesex University. Though there are several examples of real systems that can be modelled using gate-limited service, it is fair to say that the analytical models which have been developed for gate-limited systems have been difficult to use, requiring many iterations before practical results can be generated. In this paper, a detailed gate-limited bulk service queueing model based on Markov chains is explored and a numerical solution is demonstrated for simple scenarios. Quantitative results are presented and compared with a mathematical simulation. The analysis is used to develop an algorithm based on the concept of optimum operational points. The algorithm is then employed to build a high-performance server which is capable of balancing the need to prefetch for streaming applications while promptly satisfying demand misses. The algorithm is further tested using a systems simulation and then incorporated into an Experimental File System (EFS) which showed that the algorithm can be used in a real networking environment.     

重构3C服务的O2O模式探析

IT服务成本不断上升及新服务商业模式的出现,促使传统PC厂商在服务市场上不断地变革。首先介绍了3G市场的强势发展,然后分析了消费者对3C服务的需求以及3C服务市场的现状．最后介绍了联想乐享3G平台及其所提供的服务。     

我国IT服务行业的发展前景与人才储备需求分析

随着经济全球化发展趋势加快和市场竞争的加剧,如何专注自己的核心业务已经成为企业最重要的生存法则之一.2000年至今,全球IT服务外包业务高速增长带动了全球IT服务外包产业的快速发展,IT服务企业雨后春笋一般纷纷成长起来,但IT服务企业数量和规模还远远不够,IT服务人才短缺和结构的不合理严重制约了我国IT服务外包产业的快速发展.随着中国IT技术市场与国际标准的全面接轨,IT服务人才的培养和储备已经成为我国与各国IT服务行业之间竞争的主要砝码.本文分析了我国IT服务行业的发展前景,以及对IT服务人才的潜在需求,以帮助IT服务企业做好人力资源规划,同时也为高等学校培养IT服务人才提供参考依据.     

A methodical procedure for designing consumer oriented on-demand IT service propositions

IT providers are increasingly facing the challenge to adapt their previously resource oriented service portfolios in order to offer their customers services which explicitly support business processes. Such customer centric service propositions, however, seem to contradict the demand for standardized and automated operational IT processes more than traditional IT service offers, as they are even more subject to customer individual reengineering efforts due to permanently changing business requirements. In order to reconcile increased efficiency in operational processes and effectiveness in consumer oriented service propositions, we propose (1) to predefine all service propositions in consideration of both consumer oriented commitments and operational processes, and (2) to allow for standardized customization by offering a selection of complementary service propositions that extend commitments regarding customer oriented functionality and performance. Such service propositions are aligned with a company’s entities such as workplaces. Thereby the customer organization is enabled to trace, control and adjust commitments, value and expenses of IT services per entity in its business. We introduce a procedural model for designing and on-demand requesting this kind of service propositions, and we illustrate the model’s application and impact by examples taken from two large projects with an associated IT provider.     

An information system architecture for build- and engineer-to-order production of application services

In manufacturing, substantial efficiency gains have been achieved through industrialization. Key concepts of industrialization include standardization, automation, and modularization. Transferring these to IT service production promises increased efficiency. ERP systems apply such concepts and have been an integrating tool for making production for manufacturers more efficient. However, previous research has considered ERP systems for IT service providers either very broadly or only from a business or technical perspective. This article investigates how to apply the ERP system concept comprehensively to a specific type of IT service provider. To this end, application services are prescribed as being composed of three types of configuration models. This helps to achieve a composition of (IT) application services that is comparable to physical parts, and it further supports their management and automated production within an ERP system. An information system architecture with the ERP system at its core is presented. It supports application service production. All relevant service lifecycle phases are considered and a consistent domain model is provided that connects business and technical layer entities. Targeted companies can improve their application service production in terms of quality and efficiency by leveraging this novel automation- and model-based approach.     

An agent-based hybrid service delivery for coordinating internet of things and 3rd party service providers

When smart embedded devices become widely used in business and industry, many applications and services will emerge in a new Internet of Things (IoT) ecosystem. This will initiate new business opportunities in providing these novel applications and services, which integrate efficiently IoT services into business applications. Because IoT takes the reference scenarios further in terms of scale and features offered, it requires the development of suitable, scalable and available service delivery platforms that permit multiple services to coexist between IoT and 3rd party service providers. However, service delivery over IoT infrastructures is a difficult challenge that requires specific new architecture and mechanisms. This paper proposes a system architecture of hybrid service delivery that enables 3rd party service providers to create, deploy, execute, orchestrate, and manage efficiently the running instances of IoT services. In particular, this work focuses on the design and implementation of: agent-based hybrid service exposure, a hybrid service ontology engine crawler, a service enablers container, service-oriented agent lifecycle management, and an agent-mediated service lifecycle coordinator for messages dispatching and transformation between hybrid service exposure and the service enablers container. More specifically, with smart home scenarios, experimental results show that agent-based service delivery approaches could successfully coordinate between IoT and 3rd party service providers.     

2005 EDOC: meeting the challenges of enterprise computing

An increasing demand for interoperable applications exists, sparking the real-time exchange of data across borders, applications, and IT platforms. To perform these tasks, enterprise computing now encompasses a new class of groundbreaking technologies such as Web services and service-oriented architecture (SOA); business process integration and management; and middleware support, like that for utility, grid, peer-to-peer, and autonomic computing. Enterprise computing also influences the processes for business modeling, consulting, and service delivery; it affects the design, development, and deployment of software architecture, as well as the monitoring and management of such architecture. As enterprises demand increasing levels of networked information and services to carry out business processes, IT professionals need conferences like EDOC to discuss emerging technologies and issues in enterprise computing. For these reasons, what started out as the Enterprise Distributed Object Computing (EDOC) conference has come to encompass much more than just distributed objects. So this event now used the name International EDOC Enterprise Computing Conference, to recognize this broader scope yet also retain the initial conference's name recognition.     

Determinants of perceived usefulness of e-learning systems

E-learning systems are increasingly essential in universities, schools, government departments and other organizations that provide an education or training service. The objective for adopting e-learning systems is to provide students with educational services via electronic channels. The focus of this study is on the impact of IT infrastructure services and IT quality on perceptions of usefulness of e-learning systems. A model is proposed which includes five constructs: IT infrastructure services, system quality, information quality, service delivery quality, and perceived usefulness. A quantitative study was conducted at an Australian university with 720 survey responses from students who were enrolled in online courses. The results suggest that IT infrastructure services play a critical role in generating information with high quality, enhancing the aspects of e-learning system quality, and improving service delivery quality. The impact of IT infrastructure services, system quality, and information quality on perceived usefulness is fully mediated by service delivery quality. Universities need to be aware of the critical impact of IT infrastructure services and consider how investment in these services could improve system and information quality, service delivery quality, and the usefulness and success of e-learning systems.     

Scoring- und beidseitige Due-Diligence-Prozesse im Rahmen der Lieferantenauswahl beim Infrastrukturoutsourcing

Scoring and double-sided due diligence processes employed with vendor selection for IT infrastructure outsourcing Outsourcing opens the procurement of semi-finished products from business partners that are able to provide the respective processes in the required quality but at lower prices, e. g. because of bundling effects and specialization advantages. In particular, services that are not based on core-processes of an enterprise are well-suited for outsourcing. The evaluation of IT service outsourcing is difficult, because of its strategic position in enterprises. Against this background, this article describes a method to select a suitable vendor for IT infrastructure outsourcing employing scoring and double-sided due diligence processes. Our findings are based on experiences when selecting the vendor for outsourcing the European Information Technology Infrastructure (IT/I) area of the Deutsche Bank AG.     

A method for transforming knowledge discovery metamodel to ArchiMate models

Enterprise architecture has become an important driver to facilitate digital transformation in companies, since it allows to manage IT and business in a holistic and integrated manner by establishing connections among technology concerns and strategical/motivational ones. Enterprise architecture modelling is critical to accurately represent business and their IT assets in combination. This modelling is important when companies start to manage their enterprise architecture, but also when it is remodelled so that the enterprise architecture is realigned in a changing world. Enterprise architecture is commonly modelled by few experts in a manual way, which is error-prone and time-consuming and makes continuous realignment difficult. In contrast, other enterprise architecture modelling proposal automatically analyses some artefacts like source code, databases, services, etc. Previous automated modelling proposals focus on the analysis of individual artefacts with isolated transformations toward ArchiMate or other enterprise architecture notations and/or frameworks. We propose the usage of Knowledge Discovery Metamodel (KDM) to represent all the intermediate information retrieved from information systems’ artefacts, which is then transformed into ArchiMate models. Thus, the core contribution of this paper is the model transformation between KDM and ArchiMate metamodels. The main implication of this proposal is that ArchiMate models are automatically generated from a common knowledge repository. Thereby, the relationships between different-nature artefacts can be exploited to get more complete and accurate enterprise architecture representations.

     

Presentation and exchange of business models with CIMOSA-XML

In the modern competitive business world there is a frequent need for enterprises to modify their structure of business processes to become more effective in the market place. The solution to this management demand is an improved business integration which is only successful when it is supported by effective IT systems. The Esprit project PRIMA aims to create a competitive advantage for European companies in the process sector by providing a route to ‘smarter' IT investments that are effective across the whole enterprise. A process repository which will store business process models in suitable formats would provide users with appropriate views of the models, focusing only on their information needs. However, the existence of many incompatible modelling methodologies and tools makes it impossible to unify the modelling approach. Therefore it would be desirable to have a high level common modelling language. The PRIMA project has identified CIMOSA as the basis for common semantics of the business model language and the XML format, as a suitable format for the transfer of the model structure and content. The PRIMA working group, in an effort to elaborate these concepts, has developed the Document Type Definition concept (DTD) of the CIMOSA-XML meta-model, which can be used to build the partial enterprise models related to the Business Functional Requirements (BFR) of the PRIMA Process Methodology.     

基于可信第三方实现多云平台的交互和选择

随着云计算商业模式的成功推进,形成了三大主流的云计算服务模式:平台即服务、软件即服务和基础架构即服务。传统行业的供应商纷纷加入云计算的队伍。但由于激烈的竞争环境,使得云计算的标准化道路举步维艰,致使跨平台的交互和移植难以实现。同时,由于对不同的云平台没有形成统一可信的评价标准,使得众多的平台服务让用户无从选择。本文通过具体分析各种应用场景对跨平台服务的需求,得出构建"跨平台即服务"模式的必要性和必然性,提出利用可信第三方来实现"跨平台即服务"模式,给出跨平台的数据交互和移植行为在可信第三方监控下的规范化流程,并提出以可信第三方为中心的云平台安全和信誉评价标准,为企业选择合适的云平台提供参考。     

The use of fuzzy cognitive maps to simulate the information systems strategic planning process

In the early 1980s articles began to focus on Strategic Planning of Information Systems (SISP) and to argue the critical importance of Information Technology (IT) in today’s organisations. Since then, a large number of models were presented in order to analyse IT from a strategic point of view and suggest new IT projects. However, researchers urge for alternative approaches to SISP, as current ones fall short in taking into consideration both the business and IT perspectives as well as they fail to tackle the complexity of the domain and suggest specific IS opportunities. This article suggests Fuzzy Cognitive Maps (FCM) as an alternative modelling approach and describes how they can be developed and used to simulate the SISP process. FCMs were successfully developed and used in several ill-structured domains, such as decision making, policy making. The proposed FCM contains 165 variables and 210 relationships from both business and IT domains. The strength of this approach lies in its capability not only to comprehensively model qualitative knowledge which dominates strategic decision making, but also to simulate and evaluate several alternative ways of using IT in order to improve organisational performance. This approach introduces computational modelling, as well as it supports scenarios development and simulation in the SISP domain.     

CloudSim: a toolkit for modeling and simulation of cloud computing environments and evaluation of resource provisioning algorithms

Cloud computing is a recent advancement wherein IT infrastructure and applications are provided as ‘services’ to end‐users under a usage‐based payment model. It can leverage virtualized services even on the fly based on requirements (workload patterns and QoS) varying with time. The application services hosted under Cloud computing model have complex provisioning, composition, configuration, and deployment requirements. Evaluating the performance of Cloud provisioning policies, application workload models, and resources performance models in a repeatable manner under varying system and user configurations and requirements is difficult to achieve. To overcome this challenge, we propose CloudSim: an extensible simulation toolkit that enables modeling and simulation of Cloud computing systems and application provisioning environments. The CloudSim toolkit supports both system and behavior modeling of Cloud system components such as data centers, virtual machines (VMs) and resource provisioning policies. It implements generic application provisioning techniques that can be extended with ease and limited effort. Currently, it supports modeling and simulation of Cloud computing environments consisting of both single and inter‐networked clouds (federation of clouds). Moreover, it exposes custom interfaces for implementing policies and provisioning techniques for allocation of VMs under inter‐networked Cloud computing scenarios. Several researchers from organizations, such as HP Labs in U.S.A., are using CloudSim in their investigation on Cloud resource provisioning and energy‐efficient management of data center resources. The usefulness of CloudSim is demonstrated by a case study involving dynamic provisioning of application services in the hybrid federated clouds environment. The result of this case study proves that the federated Cloud computing model significantly improves the application QoS requirements under fluctuating resource and service demand patterns. Copyright © 2010 John Wiley & Sons, Ltd.     

Modeling and execution of event stream processing in business processes

The Internet of Things and Cyber-physical Systems provide enormous amounts of real-time data in the form of streams of events. Businesses can benefit from the integration of these real-world data; new services can be provided to customers, or existing business processes can be improved. Events are a well-known concept in business processes. However, there is no appropriate abstraction mechanism to encapsulate event stream processing in units that represent business functions in a coherent manner across the process modeling, process execution, and IT infrastructure layer. In this paper we present Event Stream Processing Units (SPUs) as such an abstraction mechanism. SPUs encapsulate application logic for event stream processing and enable a seamless transition between process models, executable process representations, and components at the IT layer. We derive requirements for SPUs and introduce EPC and BPMN extensions to model SPUs at the abstract and at the technical process layer. We introduce a transformation from SPUs in EPCs to SPUs in BPMN and implement our modeling notation extensions in Software AG ARIS. We present a runtime infrastructure that executes SPUs and supports implicit invocation and completion semantics. We illustrate our approach using a logistics process as running example.     

浅析网络应用系统性能优化测试简

随着网络迅速的发展,数据逐渐向数据集中化、业务处理复杂化、数据增长较快向趋势变化,并集中于后台服务处理,通过网络向成千上万的网络用户提供服务。而随着网络应用系统用户访问量的增加,网络应用系统提供服务时所出现系统响应速度太慢,加载时间过长等现象,严重影响网络应用系统提供服务的质量,由此可见,对于IT服务系统的性能测试与优化值得对其进行深入的学习和研究。     

Building Automated Data Driven Systems for IT Service Management

Enterprises and service providers are increasingly challenged with improving the quality of service delivery while containing the cost. However, it is often difficult to effectively manage the complex relationships among dynamic customer workloads, strict service level requirements, and efficient service management processes. In this paper, we present our progress on building autonomic systems for IT service management through a collection of automated data driven methodologies. This includes the design of feedback controllers for workload management, the use of simulation-optimization methodology for workforce management, and the development of machine learning models for event management. We demonstrate the applicability of the presented approaches using examples and data from a large IT service delivery environment.