Designing cloud data warehouses using multiobjective evolutionary algorithms


Dökeroǧlu T., Sert S. A. , Çinar M. S. , Coşar A.

6th International Conference on Agents and Artificial Intelligence, ICAART 2014, Angers, France, 6 - 08 March 2014, vol.1, pp.571-576 identifier

  • Publication Type: Conference Paper / Full Text
  • Volume: 1
  • Doi Number: 10.5220/0004906805710576
  • City: Angers
  • Country: France
  • Page Numbers: pp.571-576
  • Keywords: Cloud, Elasticity, Multiobjective data warehouse design, Virtualization

Abstract

DataBase as a Service (DBaaS) providers need to improve their existing capabilities in data management and balance the efficient usage of virtual resources to multi-users with varying needs. However, there is still no existing method that concerns both with the optimization of the total ownership price and the performance of the queries of a Cloud data warehouse by taking into account the alternative virtual resource allocation and query execution plans. Our proposed method tunes the virtual resources of a Cloud to a data warehouse system, whereas most of the previous studies used to tune the database/queries to a given static resource setting. We solve this important problem with an exact Branch and Bound algorithm and a robust Multiobjective Genetic Algorithm. Finally, through several experiments we conclude remarkable findings of the algorithms we propose.