III-COR: Collaborative Research: Graceful Evolution and Historical Queries in Information Systems-- a Unified Approach
Database schema evolution is a constant in the life-cycle of Information Systems (IS), and a source of major costs for maintenance, upgrading, and service down time. The traditional process of installing a new schema, converting the database, and rewriting applications is slow and laborious. Instead, this project develops the novel technology whereby the schema evolution problem is reduced to coordinating mappings between multiple concurrent versions of schema, applications, and database. The project's approach consists of developing: (i) XML-based architectures for unifying the management of evolving data and metadata, (ii) methods for capturing evolution via schema mappings, (iii) efficient mapping techniques for queries and applications. These advances will enable the development of the MetaManager, a system that supports: (a) preserving and querying database histories, and (b) better planning on how-to evolve current schema versions, via evaluation and testing of ``what-if'' scenarios. Its functionality and performance are validated using various testbeds, including the SDSC Storage Request Broker, which hosts scientific data for research groups ranging from astrophysicists to biologists.
This novel and timely approach provides a solution to both the evolution and preservation of IS. Because of the key role played by IS, a broad range of scientific, educational, and economic activities will benefit. Project funds support training of PhD students while undergraduate research interns are trained on schema-evolution scenarios using the MetaManager. The technology is a part of database design courses. Results are disseminated via publications, reports and demos which are available from:
www.cs.ucr.edu/~tsotras/meta-manager http://wis.cs.ucla.edu/projects/meta-manager http://db.ucsd.edu/people/alin/meta-manager
