【正文】 ssrelease/。 [IBM08b] IBM 公司， “ 幻 影 ： 虛 擬 機(jī) 映 像 的 數(shù) 據(jù) ” ， 6月 08 。 [Lud06]二 Lud228。李，學(xué)者道，華趙， “ 科學(xué)工作流程管理和系統(tǒng)的開普勒 ” 并發(fā)與計算：實踐與經(jīng)驗，對電網(wǎng)系統(tǒng)的工作流程專刊， 18卷，第 10期（ 2020年 8月），頁數(shù)： 1039 1065,2020。 [New05]新人，埃里克 ， Lomow，格雷格， ： 理解 SOA 與 Web 服務(wù)， ‖艾迪生韋斯利，書號 0321180860， 2020。 [Rei07] j 的默， “ 夢在 ” 云 “ 與 XIOS 網(wǎng)絡(luò)操作系統(tǒng) ” ，四月 8， 2020， 云與 的 xios weboperating 。 14，第 114132， 1999。 [Tho05] ERL的，托馬斯， “ 面向服務(wù)架構(gòu)：概念，技術(shù)和設(shè)計 ” 上鞍河： Prentice Hall 出版 社的 PTR。 [Van08]標(biāo)記 VanderWiele， “ IBM的云計算研究計劃 ” 主題在 ICVCI 2020年中，RTP， NC，美國， 1516 2020年 5月的談話。 [VMW07] VMWare 的， “ 開放虛擬機(jī)格式 白皮書的 OVF規(guī)范 ” ， ， 2020年， 。 [Vou99] Vouk米，河屬 Klevans，并 ， “ 工作流程和網(wǎng)絡(luò)教育的最終用戶服務(wù)質(zhì)量問題 ” IEEE期刊。 [Vou08a]姆拉登納萊 Vouk，山姆埃弗里特，邁克爾 Bugaev，安迪庫爾特，亞倫皮勒，安迪 。 使用 DOS *，亨利謝弗，埃里克窗臺，莎拉斯坦，喬希湯普森 ” 39。 利用虛擬計算實驗室（ VCL）的云計算技術(shù)在電力。 [Vou08b]馬 Vouk， “ 虛擬化技術(shù)的信息資源，電子商務(wù) ” ：管理的角度 2020年，第 5版 ?頭巾， Prentice Hall 出版社出版業(yè)務(wù)，才會出現(xiàn)。 Cloud Computing – Issues, Research and Implementations Mladen A. Vouk Department of Computer Science, North Carolina State University, Raleigh, NC 27695, USA Abstract: ―Cloud‖ puting – a relatively recent term, builds on decades of research in virtualization, distributed puting, utility puting, and more recently working, web and software services. It implies a service oriented architecture, reduced information technology overhead for the enduser, great flexibility, reduced total cost of ownership, ondemand services and many other things. This paper discusses the concept of ―cloud‖ puting, issues it tries to address, related research topics, and a ―cloud‖ implementation available today. Keywords: Cloud Computing。 virtualization。 endtoend quality of service 1. Introduction ―Cloud puting‖ is the next natural step in the evolution of ondemand information technology services and products. To a large extent cloud puting will be based on virtualized resources. Cloud puting predecessors have been around for some time now [., AEC08, Con08, Fos04, Glo08, Had08, IBM07c, Nao07, Net06, Reo07, VCL04], but the term became ―popular‖ sometime in October 2020 when IBM and Google announced a collaboration in that domain [., Loh07, IBM07a]. This was followed by IBM39。me=escallout 5 ., 6 ., m and 7 ., en/Processors/ProductInformation/0,30_118_8826_14287, 8 9 10 11 12 13 Figure 2 illustrates four broad sets of nonexclusive user categories: System or Cyberinfrastructure (CI) developers, developers (authors) of different ponent services and underlying applications, technology and domain personnel that integrates basic services into posite services and their orchestrations (workflows) and delivers those to endusers, and finally users of simple and posite services. User categories also include domain specific groups, and indirect users such as stakeholders, policy makers, and so on. Functional and usability requirements derive, in 5 most part, directly from the user profiles. An example, and a discussion, of user categories appropriate in the educational domain can be found in [Vou99]. Specifically, a successful ―cloud‖ in that domain the K20 and continuing education would be expected to: a. Support large numbers of users that range from very naive to very sophisticated (millions of student contact hours per year). b. Support construction and delivery of content and curricula for these users. For that, the system needs to provide support and tools for thousands of instructors, teachers, professors, and others that serve the students. c. Generate adequate content diversity, quality, and range. This may require many hundreds of authors. d. Be reliable and costeffective to operate and maintain. The effort to maintain the system should be relatively small, although introduction of new paradigms and solutions may require a considerable startup development effort. . Developers Cyber Infrastructure developers who are responsible for development and maintenance of the Cloud framework. They develop and integrate system hardware, storage, works, interfaces, administration and management software, munications and scheduling algorithms, services authoring tools, workflow generation and resource access algorithms and software, and so on. They must be experts in specialized areas such as works, putational hardware, storage, lowlevel middleware, operating systems imaging, and similar. In addition to innovation and development of new ―cloud‖ functionalities, they also are responsible for keeping the plexity of the framework away from the higherlevel users through judicious abstraction, layering and middleware. One of the lessons learned from, for example, ―grid‖ puting efforts is that the plexity of the underlying infrastructure and middlware can be daunting, and if exposed can impact wider adoption of a solution. . Authors Service authors are developers of individual baseline ―images‖ and services that may be used directly, or may be integrated into more plex service aggregates and workflows by service provisioning and integration experts. In the context of the VCL 6 technology, an ―image‖ is a tangible abstraction of the software stack [Ave07, Vou08a]. It incorporates a) any baseline operating system, and if virtualization is needed for scalability, a hypervisor layer, b) any desired middleware or application that runs on that operating system, and c) any enduser access solution that is appropriate (., ssh, web, RDP, VNC, etc.). Images can be loaded on ―baremetal‖, or into an operating system/application virtual environment of choice. When a user has the right to create an image, that user usually starts with a ―NoApp‖ or a baseline image (., Win XP or Linux) and extends it with his/her applications. Similarly, when an author