Cloud Computing: A Perspective Study

FIND A SOLUTION AT Academic Writers Bay

Rochester Institute of TechnologyRIT Scholar WorksPresentations and other scholarship2008Cloud Computing: A Perspective StudyLizhe WangRochester Institute of TechnologyGregor von LaszewskiRochester Institute of TechnologyMarcel KunzeKarlsruhe Institute of TechnologyJie TaoKalrsruhe Institute of TechnologyFollow this and additional works at: Conference Proceeding is brought to you for free and open access by RIT Scholar Works. It has been accepted for inclusion in Presentations andother scholarship by an authorized administrator of RIT Scholar Works. For more information, please contact [email protected]Recommended CitationWang, L., von Laszewski, G., Younge, A. et al. New Gener. Comput. (2010) 28: 137. Computing: a Perspective StudyLizhe WANG, Gregor VON LASZEWSKIService Oriented Cyberinfrastruture Lab, Rochester Inst. of Tech.102 Lomb Memorial Drive, Rochester, NY 14623, U.S.Lizhe.Wang, [email protected]Marcel KUNZE, Jie TAOSteinbuch Centre for Computing, Karlsruhe Institute of TechnologyHermann-von-Helmholtz-Platz 1, Eggenstein-Leopoldshafen, GermanyMarcel.Kunze, [email protected]Received 1 Dec 2008Abstract The Cloud computing emerges as a new computing paradigmwhich aims to provide reliable, customized and QoS guaranteed dynamiccomputing environments for end-users. In this paper, we study the Cloudcomputing paradigm from various aspects, such as definitions, distinctfeatures, and enabling technologies. This paper brings an introductionalreview on the Cloud computing and provide the state-of-the-art of Cloudcomputing technologies.Keywords Cloud Computing, Grid Computing, Cyberinfrastructure,Distributed Computing§1 IntroductionThe Cloud computing, which was coined in late of 2007, currently emergesas a hot topic due to its abilities to offer flexible dynamic IT infrastructures, QoSguaranteed computing environments and configurable software services. As reported in the Google trends shown in Figure 1, the Cloud computing (the blue2 Marcel KUNZE, Jie TAOFig. 1 Cloud computing in Google trendsline), which is enabled by virtualization technology (the yellow line), has alreadyoutpaced the Grid computing 8) (the red line).Numerous projects within industry and academia have already started,for example the RESERVOIR project 27) – an IBM and European Union jointresearch initiative for Cloud computing, Amazon Elastic Compute Cloud 13),IBM’s Blue Cloud 10), scientific Cloud projects such as Nimbus 24) and Stratus 31),and OpenNEbula 26). HP, Intel Corporation and Yahoo! Inc. recently announcedthe creation of a global, multi-data center, open source Cloud computing testbed for industry, research and education 3).There are still no widely accepted definitions for the Cloud computing albeit the Cloud computing practice has attracted much attention. Severalreasons lead into this situation:• Cloud computing involves researchers and engineers from various backgrounds, e.g., Grid computing, software engineering and database. Theywork on Cloud computing from different viewpoints.• Technologies which enable the Cloud computing are still evolving andprogressing, for example, Web 2.0 and Service Oriented Computing.• Existing computing Clouds still lack large scale deployment and usage,which would finally justify the concept of Cloud computing.In this paper we attempt to contribute the concept of Cloud computing: definition, functionality, enabling technology and typical applications. Theremaining parts of this paper are organized as follows. Section 2 discusses theconcept of Cloud computing, Section 3 presents the functionalities of the Cloudcomputing, Section 4 reviews the distinct features of the Cloud computing, andCloud Computing: a Perspective Study 3Section 5 enumerates the enabling technologies for building computing Clouds.Section 6 concludes the whole paper.§2 Definition of Cloud ComputingCloud computing is becoming one of the next IT industry buzz words:users move out their data and applications to the remote “Cloud” and then accessthem in a simple and pervasive way. This is again a central processing use case.Similar scenario occurred around 50 years ago: a time-sharing computing serverserved multiple users. Until 20 years ago when personal computers came to us,data and programs were mostly located in local resources. Certainly currentlythe Cloud computing paradigm is not a recurrence of the history. 50 years agowe had to adopt the time-sharing servers due to limited computing resources.Nowadays the Cloud computing comes into fashion due to the need to buildcomplex IT infrastructures. Users have to manage various software installations,configuration and updates. Computing resources and other hardware are proneto be outdated very soon. Therefore outsourcing computing platforms is a smartsolution for users to handle complex IT infrastructures.At the current stage, the Cloud computing is still evolving and thereexists no widely accepted definition. Based on our experience, we propose anearly definition of Cloud computing as follows:A computing Cloud is a set of network enabled services, providing scalable, QoS guaranteed, normally personalized, inexpensive computing infrastructures on demand, which could be accessed in a simple and pervasive way.§3 Functional Aspects of Cloud ComputingConceptually, users acquire computing platforms or IT infrastructuresfrom computing Clouds and then run their applications inside. Therefore, computing Clouds render users with services to access hardware, software and dataresources, thereafter an integrated computing platform as a service, in a transparent way:Hardware as a Service (HaaS):Hardware as a Service was coined possibly in 2006. As the result ofrapid advances in hardware virtualization, IT automation and usagemetering & pricing, users could buy IT hardware, or even an entire4 Marcel KUNZE, Jie TAOdata center, as a pay-as-you-go subscription service. The HaaS isflexible, scalable and manageable to meet your needs 2). Examplescould be found at Amazon EC2 13), IBM’s Blue Cloud project 10),Nimbus 24), Eucalyptus 18) and Enomalism 17).Software as a Service (SaaS):Software or an application is hosted as a service and provided to customers across the Internet. This mode eliminates the need to installand run the application on the customer’s local computers. SaaStherefore alleviates the customer’s burden of software maintenance,and reduces the expense of software purchases by on-demand pricing.An early example of the SaaS is the Application Service Provider(ASP) 15). The ASP approach provides subscriptions to softwarethat is hosted or delivered over the Internet. Microsoft’s “Software +Service” 30) shows another example: a combination of local softwareand Internet services interacting with one another. Google’s Chromebrowser 21) gives an interesting SaaS scenario: a new desktop could beoffered, through which applications can be delivered (either locally orremotely) in addition to the traditional Web browsing experience.Data as a Service (DaaS):Data in various formats and from multiple sources could be accessedvia services by users on the network. Users could, for example, manipulate the remote data just like operate on a local disk or access thedata in a semantic way in the Internet.Amazon Simple Storage Service (S3) 14) provides a simple Web services interface that can be used to store and retrieve, declared byAmazon, any amount of data, at any time, from anywhere on theWeb. The DaaS could also be found at some popular IT services,e.g., Google Docs 22) and Adobe Buzzword 12). ElasticDrive 16) is adistributed remote storage application which allows users to mount aremote storage resource such as Amazon S3 as a local storage device.Based on the support of the HaaS, SaaS and DaaS, the Cloud computingin addition can deliver the Infrastructure as a Service (IaaS) for users. Usersthus can on-demand subscribe to their favorite computing infrastructures withrequirements of hardware configuration, software installation and data accessdemands. Figure 2 shows the relationship between the services. The GoogleCloud Computing: a Perspective Study 5App Engine 20) is an interesting example of the IaaS. The Google App Engineenables users to build Web applications with Google’s APIs and SDKs acrossthe same scalable systems, which power the Google applications.SaaS HaaS DaaSCloud resoruceApplicationScientific CloudIaaSFig. 2 Cloud functionalities§4 Why is Cloud Computing Distinct?The Cloud computing distinguishes itself from other computing paradigms,like Grid computing, Global computing, Internet Computing in the following aspects:User-centric interfaces.Cloud services should be accessed with simple and pervasive methods.In fact, the Cloud computing adopts the concept of Utility computing. In other words, users obtain and employ computing platforms incomputing Clouds as easily as they access a traditional public utility (such as electricity, water, natural gas, or telephone network). Indetail, the Cloud services enjoy the following features:– The Cloud interfaces do not force users to change their workinghabits and environments, e.g., programming language, compiler and operating system. This feature differs Cloud computing from Grid computing as Grid users have to learn new Gridcommands & APIs to access Grid resources & services.– The Cloud client software which is required to be installed locally is lightweight. For example, the Nimbus Cloudkit client6 Marcel KUNZE, Jie TAOsize is around 15MB.– Cloud interfaces are location independent and can be accessedby some well established interfaces like Web services frameworkand Internet browser.On-demand service provisioning.Computing Clouds provide resources and services for users on demand.Users can customize and personalize their computing environmentslater on, for example, software installation, network configuration, asusers usually own administrative privileges.QoS guaranteed offer.The computing environments provided by computing Clouds can guarantee QoS for users, e.g., hardware performance like CPU speed, I/Obandwidth and memory size.The computing Cloud renders QoS in general by processing ServiceLevel Agrement (SLA) with users – a negotiation on the levels ofavailability, serviceability, performance, operation, or other attributesof the service like billing and even penalties in the case of violation ofthe SLA.Autonomous System.The computing Cloud is an autonomous system and it is managedtransparently to users. Hardware, software and data inside cloudscan be automatically reconfigured, orchestrated and consolidated topresent a single platform image, finally rendered to users.Scalability and flexibility.The scalability and flexibility are the most important features thatdrive the emergence of the Cloud computing. Cloud services andcomputing platforms offered by computing Clouds could be scaledacross various concerns, such as geographical locations, hardware performance, software configurations. The computing platforms shouldbe flexible to adapt to various requirements of a potentially large number of users.§5 Enabling Technologies behind Cloud ComputingA number of enabling technologies contribute to Cloud computing, sevCloud Computing: a Perspective Study 7eral state-of-the-art techniques are identified here:Virtualization technology.Virtualization technologies partition hardware and thus provide flexible and scalable computing platforms. Virtual machine techniques,such as VMware 34) and Xen 1), offer virtualized IT-infrastructures ondemand. Virtual network advances, such as VPN 7), support userswith a customized network environment to access Cloud resources.Virtualization techniques are the bases of the Cloud computing sincethey render flexible and scalable hardware services.Orchestration of service flow and workflow.Computing Clouds offer a complete set of service templates on demand, which could be composed by services inside the computingCloud. Computing Clouds therefore should be able to automaticallyorchestrate services from different sources and of different types toform a service flow or a workflow transparently and dynamically forusers.Web service and Service Oreinted Architecture (SOA).Computing Cloud services are normally exposed as Web services,which follow the industry standards such as WSDL 33), SOAP 28) andUDDI 25). The services organization and orchestration inside Cloudscould be managed in a Service Oriented Architecture (SOA). A set ofCloud services furthermore could be used in a SOA application environment, thus making them available on various distributed platformsand could be further accessed across the Internet.Web 2.0.Web 2.0 is an emerging technology describing the innovative trendsof using World Wide Web technology and Web design that aims toenhance creativity, information sharing, collaboration and functionality of the Web 6). The essential idea behind Web 2.0 is to improvethe interconnectivity and interactivity of Web applications. The newparadigm to develop and access Web applications enables users accessthe Web more easily and efficiently. Cloud computing services in nature are Web applications which render desirable computing serviceson demand. It is thus a natural technical evolution that the Cloudcomputing adopts the Web 2.0 technique.8 Marcel KUNZE, Jie TAOWorld-wide distributed storage system.A Cloud storage model should foresee:– A network storage system, which is backed by distributed storage providers (e.g., data centers), offers storage capacity forusers to lease. The data storage could be migrated, merged,and managed transparently to end users for whatever data formats. Examples are Google File System 9) and Amazon S3 14).A Mashup 11) is a Web application that combines data frommore than one source into a single integrated storage tool. TheSmugMug 29) is an example of Mashup, which is a digital photosharing Web site, allowing the upload of an unlimited number ofphotos for all account types, providing a published API whichallows programmers to create new functionality, and supporting XML-based RSS and Atom feeds.– A distributed data system which provides data sources accessedin a semantic way. Users could locate data sources in a largedistributed environment by the logical name instead of physicallocations. Virtual Data System (VDS) 32) is good reference.Programming model.Users drive into the computing Cloud with data and applications.Some Cloud programming models should be proposed for users toadapt to the Cloud infrastructure. For the simplicity and easy accessof Cloud services, the Cloud programming model, however, should notbe too complex or too innovative for end users.The MapReduce 4, 5) is a programming model and an associated implementation for processing and generating large data sets across theGoogle worldwide infrastructures. The MapReduce model firstly involves applying a “map” operation to some data records – a set ofkey/value pairs, and then processes a “reduce” operation to all thevalues that shared the same key. The Map-Reduce-Merge 35) methodevolves the MapReduce paradigm by adding a “merge” operation.Hadoop 23) is a framework for running applications on large clusters built of commodity hardware. It implements the MapReduceparadigm and provides a distributed file system – the Hadoop Distributed File System. The MapReduce and the Hadoop are adoptedby recently created international Cloud computing project of Yahoo!,Cloud Computing: a Perspective Study 9Intel and HP 3, 19).§6 ConclusionThis paper reviews the recent advances of Cloud computing and presentsour views on Cloud computing: definition, key features and enabling technologies. The perspective study aims to contribute the evolution of the Cloud computing paradigm.10 Marcel KUNZE, Jie TAOReferences1) P. Barham, B. Dragovic, K. Fraser, S. Hand, T. L. Harris, A. Ho, R. Neugebauer,I. Pratt, and A. Warfield. Xen and the art of virtualization. In Proceedingsof the 19th ACM Symposium on Operating Systems Principles, pages 164–177,New York, U. S. A., Oct. 2003.2) Here comes HaaS [URL]. comes haas.php/,access on June 2008.3) Global Cloud computing test bed [URL]., access onJuly 2008.4) J. Dean. Mapreduce and other building blocks for large-scale distributed systems at google. In Proceedings of the USENIX Annual Technical Conference,2007.5) J. Dean and S. Ghemawat. Mapreduce: simplified data processing on largeclusters. Commun. ACM, 51(1):107–113, 2008.6) Web 2.0 definition [URL]. 2/, access on June 2008.7) B. Gleeson etc. A framework for IP based virtual private networks. RFC2764,The Internet Engineering Task Force, Feb. 2000.8) I. Foster and C. Kesselman. The Grid: blueprint for a new computing infrastructure. Morgan Kaufmann, 1998.9) S. Ghemawat, H. Gobioff, and S. Leung. The Google file system. In Proceedingsof the 19th ACM Symposium on Operating Systems Principles, pages 29–43,2003.10) IBM Blue Cloud project [URL].,access on June 2008.11) Mashup project[URL]. web application hybrid/, access on June2008.12) Adobe Buzzword [URL]., access on Sep. 2008.13) Amazon Elastic Compute Cloud [URL]., access on Nov. 2007.14) Amazon Simple Storage Service [URL]., access on Sep. 2008.15) Application Service Provider [URL].,access on Sep. 2008.16) Elasticdrive Project [URL]., access on Sep. 2008.17) Enomalism Project [URL]., access on Sep. 2008.18) Eucalyptus Project [URL]., access on Sep. 2008.Cloud Computing: a Perspective Study 1119) Global Cloud Computing Research Test Bed Wiki [URL].,access on Oct. 2008.20) Google App Engine [URL]., access on Sep. 2008.21) Google Chrome [URL]., access on Sep. 2008.22) Google Docs [URL]., access on Sep. 2008.23) Hadoop [URL]., access on Sep. 2008.24) Nimbus Project [URL]., access on June 2008.25) OASIS UDDI Specification [URL].,access on June 2008.
OpenNEbula Project [URL].2008., access on Apr.
27) Reservoir Project [URL].,access on June 2008.28) Simple Object Access Protocol (SOAP) [URL]., access on Nov. 2007.29) SmugMug [URL]., access on June 2008.30) Software + Services [URL]., access on June 2008.31) Status Project [URL]., access on June 2008.32) Virtual Data System [URL]., access on Nov. 2007.33) Web Service Description Language (WSDL) [URL]., access on Nov. 2007.34) VMware virtualization technology [URL]., access on Nov. 2007.35) H. Yang, A. Dasdan, R. Hsiao, and D. S. Parker Jr. Map-reduce-merge: simplified relational data processing on large clusters. In Proceedings of the ACMSIGMOD International Conference on Management of Data, pages 1029–1040,2007.

Order from Academic Writers Bay
Best Custom Essay Writing Services