Mapping High-Level Application Requirements onto Low-Level Cloud Resources

• 作者: Alan Stewart Terence Harmer Yih Leong Sun
• 来源期刊: 软件工程与应用(英文)
• 学科: 工学
• 关键词: CLOUD COMPUTING RESOURCE MAPPING CLOUD Ontology COST Model
• 年，卷（期）: 2012,（11）
• 页码范围: 894-902
• 页数: 9页
• 分类号: TP3

摘要

Cloud computing has created a paradigm shift that affects the way in which business applications are developed. Many business organizations use cloud infrastructures as platforms on which to deploy business applications. Increasing numbers of vendors are supplying the cloud marketplace with a wide range of cloud products. Different vendors offer cloud products in different formats. The cost structures for consuming cloud products can be complex. Finding a suitable set of cloud products that meets an application’s requirements and budget can be a challenging task. In this paper, an ontology-based resource mapping mechanism is proposed. Domain-specific ontologies are used to specify high-level application’s requirements. These are then translated into high-level infrastructure ontologies which then can be mapped onto low-level descriptions of cloud resources. Cost ontologies are proposed for cloud resources. An exemplar media transcoding and delivery service is studied in order to illustrate how high-level requirements can be modeled and mapped onto cloud resources within a budget constraint. The proposed ontologies provide an application-centric mechanism for specifying cloud requirements which can then be used for searching for suitable resources in a multi-provider cloud environment.