A Declarative Recommender System for Cloud Infrastructure Services Selection

Free registration required

Executive Summary

The cloud infrastructure services landscape advances steadily leaving users in the agony of choice. Therefore, the authors present CloudRecommender, a new declarative approach for selecting Cloud-based infrastructure services. CloudRecommender automates the mapping of users' specified application requirements to cloud service configurations. They formally capture cloud service configurations in ontology and provide its implementation in a structured data model which can be manipulated through both regular expressions and SQL. By exploiting the power of a visual programming language (widgets), CloudRecommender further enables simplified and intuitive cloud service selection. They describe the design and a prototype implementation of CloudRecommender, and demonstrate its effectiveness and scalability through a service configuration selection experiment on most of today's prominent cloud providers including Amazon, Azure, and GoGrid.

  • Format: PDF
  • Size: 858.18 KB