Cost-effective replication-based storage for reliability assurance of Big Data in the Cloud

In this thesis, we investigate the trade-off between data storage cost and data reliability assurance for the big data in the Cloud. The research is motivated by a scientific application for astrophysics pulsar searching surveys, which is of typical data-intensive characteristics and contains complex and time consuming tasks that process hundreds of terabytes of data. In order to facilitate the migration of the application into the Cloud, our novel research stands from the Cloud storage service providers' perspective and investigates the issue on how to provide cost-effective data storage while meeting the data reliability requirement throughout the whole Cloud data lifecycle.