2014 IEEE DOTNET CLOUD COMPUTING PROJECT A mechanism design approach to resource procurement in cloud computing
Post on 26-Jun-2015
Embed Size (px)
DESCRIPTIONTo Get any Project for CSE, IT ECE, EEE Contact Me @ 09666155510, 09849539085 or mail us - email@example.com-Visit Our Website: www.finalyearprojects.org
- 1. GLOBALSOFT TECHNOLOGIESIEEE PROJECTS & SOFTWARE DEVELOPMENTSIEEE FINAL YEAR PROJECTS|IEEE ENGINEERING PROJECTS|IEEE STUDENTS PROJECTS|IEEEBULK PROJECTS|BE/BTECH/ME/MTECH/MS/MCA PROJECTS|CSE/IT/ECE/EEE PROJECTSCELL: +91 98495 39085, +91 99662 35788, +91 98495 57908, +91 97014 40401Visit: www.finalyearprojects.org Mail to:ieeefinalsemprojects@gmai l.comA Mechanism Design Approach to ResourceProcurement in Cloud ComputingAbstractWe present a cloud resource procurement approach which not only automates theselection of an appropriate cloud vendor but also implements dynamic pricing. Three possiblemechanisms are suggested for cloud resource procurement: cloud-dominant strategy incentivecompatible (C-DSIC), cloud-Bayesian incentive compatible (C-BIC), and cloud optimal (C-OPT).C-DSIC is dominant strategy incentive compatible, based on the VCG mechanism, and isa low-bid Vickrey auction. C-BIC is Bayesian incentive compatible, which achieves budgetbalance. C-BIC does not satisfy individual rationality. In C-DSIC and C-BIC, the cloud vendorwho charges the lowest cost per unit Qos is declared the winner. In C-OPT, the cloud vendorwith the least virtual cost is declared the Winner. C-OPT overcome the limitations of both C-DSICand C-BIC. C-OPT is not only Bayesian incentive compatible, but also individuallyrational. Our experiments indicate that the resource procurement cost decreases with increase innumber of cloud vendors irrespective of the mechanisms. We also propose a procurementmodule for a cloud broker which can implement C-DSIC, C-BIC, or C-OPT to perform resourceprocurement in a cloud computing context. A cloud broker with such a procurement moduleenables users to automate the choice of a cloud vendor among many with diverse offerings, andis also an essential first step toward implementing dynamic pricing in the cloud
2. Existing SystemResource procurement of cloud resources is an interesting and yet unexplored area incloud computing. Cloud vendors follow a fixed pricing strategy (pay as you go)for pricingtheir resources and do not provide any incentive to their users to adjust consumption patternsaccording to availability or other factors.Most cloud vendors use the pay-as-you-go model. Many are loath to negotiate contractsas they lack understanding of a sound theoretical basis for dynamic pricing. The defaultagreement offered by a vendor often contractually benefits the vendor but not the user, resultingin a mismatch with user requirements. Hence, this kind of pricing favors the cloud vendor. Also,there is no clear commitment on SLAs.Proposed SystemEach cloud user has resource requirements. The users perform reverse auctions forprocuring resources (which are also called procurement auctions). Cloud vendors offer resources,but with varying costs and quality metrics. The goal of the cloud user is to minimize the totalcost of procuring resources without compromising quality of service. To minimize theprocurement cost, it is necessary for the cloud user to know the real costs of cloud vendors. Auser announces its specifications for desired resources and quality of service to all cloud vendors,with the broker acting as a middleman. The cloud vendors decide whether to participate in theauction based on the user information and submit their bids to the broker.Advantage Costs and tasks are uniformly distributed. The average procurement cost is calculated inevery mechanism and compared.Modules User Cloud broker Cloud provider 3. 1. UserIt contains following steps User Registration Login File Upload View accepted Files Request for space Download(a)User RegistrationIn this module new user register the information in order to use the cloud for space.(b)LoginIn this module user can login by using his/her username and password.(c)File UploadIn this module each user can upload the file and requirements to the cloud broker forprovider allocation.(d)View Accepted FilesIn this module each user can view their own file is accepted or not.(e)Request for SpaceIn this module each user sent the request to the cloud broker for upload their file in cloud(f)DownloadIn this module user can download their files for future use.2. Cloud Broker: Login Accept Files 4. View provider space Provider allocation(a)LoginBy this module cloud broker can enter into process by using his name and password.(b)Accept FilesIn this module the broker can accept the user by accepting and rejecting their file dependson their cost.(c)View Provider SpaceIn this module broker can view available space in each cloud server(d)Provider AllocationThis component validates the user resource requirements. The validated requirements arebroadcasted to all the cloud vendors. The cloud vendors respond with the assumed QoSparameters and cost. This information is validated and sent to the auction manager.3. Cloud Provider Module:In this module each user can upload the files depending on their cost to upload their filesin cloud server (i.e.) cloud provider.The cloud provider can view the files are upload to server.System SpecificationHardware Requirements System : Pentium IV 2.4 GHz. Hard Disk : 40 GB. Floppy Drive : 1.44 Mb. Monitor : 14 Colour Monitor. Mouse : Optical Mouse. Ram : 512 Mb. 5. Software Requirements Operating system : Windows 7. Coding Language : ASP.Net with C# Data Base : SQL Server 2008.ConclusionCurrently, the cloud user pays a fixed price for resources or services. This typeof pricing is called fixed pricing. Fixed pricing is very popular with telecom providers.On the flipside, there is no provision for incentives for users in the fixed strategy.Resource procurement is not only an important problem in cloud computing but is also anunexplored area. Currently, resource procurement is done manually and there is apressing need to automate it. To automate procurement, we have presented threemechanisms: C-DSIC, C-BIC, and C-OPT. C-DSIC is a lowbid Vickrey auction. It isallocative efficient and individual rational but not budget balanced. If the mechanism isnot budget balanced, then an external agency has to provide money to performprocurement.C-BIC is a weaker strategy compared to C-DSIC and it is Bayesianincentive compatible. In C-BIC, vendors reveal the truth only if other vendors reveal thetruth, unlike C-DISC where vendors reveal the truth irrespective of others choices. C -BIC achieves budget balance and a locative efficiency but not individual rationalitys-OPT achieves both Bayesian incentive compatibility and individual rationality, which theother two mechanisms cannot achieve. This mechanism is immune to both overbiddingand underbidding. If a cloud vendor overbids, then the incentive is reduced. If itunderbids, then it may not be a winner. C-OPT is more general compared to both C-DSICand C-BICeven if cloud vendors use different distributions for cost and QoS, we cansafely use C-OPT. Hence, C-OPT is the preferred mechanism in more cases in the realworld. The experiments reveal an interesting pattern. The resource procurement costreduces as the number of cloud vendors increase, irrespective of the mechanism 6. implemented. The cost in C-BIC reduces more significantly, compared to the other twomechanisms.