{"title":"Modelling Cloud Federation: A Fair Profit Distribution Strategy Using the Shapley Value","authors":"Kun Ma, A. Bagula, H. Mauwa, A. Celesti","doi":"10.1109/FiCloud.2018.00063","DOIUrl":null,"url":null,"abstract":"Cloud computing provides software (Software as a Service), platform (Platform as a Service) and infrastructure (Infrastructure as a Service) services to its users by integrating IT resources into a large-scale and scalable resource pool through the virtualisation technology. However, the single cloud resource provider model currently implemented by many providers may fail short to meet the dynamic nature of cloud users' requirements. Cloud federation can mitigate this issue by optimising cloud resource allocation through sharing and re-usability of available resources. This paper revisit the problem of cloud engineering by tackling the key issue of the fair distribution of profit between cloud resource providers, which, to the best of our knowledge, has only been scarcely addressed by the research and practitioners' community. We propose a method that enables the cloud federation to map the contribution of resources of the participants to the federations into a quality of service metric used to achieve a cloud federation. Building upon a federation game implementation, we reveal the possibilities and benefits of different federation compositions using the Shapley value of each resource provider as a way of implementing a fair profit sharing strategy. Using extensions of the CloudSim package, we present simulation results that demonstrate the fairness of our proposed method and strategy.","PeriodicalId":174838,"journal":{"name":"2018 IEEE 6th International Conference on Future Internet of Things and Cloud (FiCloud)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2018-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"5","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2018 IEEE 6th International Conference on Future Internet of Things and Cloud (FiCloud)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/FiCloud.2018.00063","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 5
Abstract
Cloud computing provides software (Software as a Service), platform (Platform as a Service) and infrastructure (Infrastructure as a Service) services to its users by integrating IT resources into a large-scale and scalable resource pool through the virtualisation technology. However, the single cloud resource provider model currently implemented by many providers may fail short to meet the dynamic nature of cloud users' requirements. Cloud federation can mitigate this issue by optimising cloud resource allocation through sharing and re-usability of available resources. This paper revisit the problem of cloud engineering by tackling the key issue of the fair distribution of profit between cloud resource providers, which, to the best of our knowledge, has only been scarcely addressed by the research and practitioners' community. We propose a method that enables the cloud federation to map the contribution of resources of the participants to the federations into a quality of service metric used to achieve a cloud federation. Building upon a federation game implementation, we reveal the possibilities and benefits of different federation compositions using the Shapley value of each resource provider as a way of implementing a fair profit sharing strategy. Using extensions of the CloudSim package, we present simulation results that demonstrate the fairness of our proposed method and strategy.
云计算通过虚拟化技术,将IT资源整合成一个大规模的、可扩展的资源池,为用户提供软件(software as a Service)、平台(platform as a Service)和基础设施(infrastructure as a Service)服务。然而,目前由许多提供商实现的单一云资源提供商模型可能无法满足云用户需求的动态性。云联合可以通过共享和重用可用资源来优化云资源分配,从而缓解这个问题。本文通过解决云资源提供商之间利润公平分配的关键问题来重新审视云工程问题,据我们所知,这一问题几乎没有得到研究和从业者社区的解决。我们提出了一种方法,使云联盟能够将参与者对联盟的资源贡献映射到用于实现云联盟的服务质量度量中。在联邦游戏实现的基础上,我们使用每个资源提供者的Shapley值作为实现公平利润分享策略的一种方式,揭示了不同联邦组合的可能性和好处。使用CloudSim包的扩展,我们给出了仿真结果,证明了我们提出的方法和策略的公平性。