On the specification of extract, transform, and load patterns behavior: A domain-specific language approach

Abstract

During the last few years, many research efforts have been done to improve the design of extract, transform, and load (ETL) models systems. Still, ETL systems are considered very time-consuming, error-prone, and complex involving several participants from different knowledge domains. The ETL processes are one of the most important components of a data warehousing system that are strongly influenced by the complexity of business requirements, their changing and evolution. These aspects influence not only the structure of the data warehouse itself but also the structures of the data sources involved with. To minimize the negative impact of such variables, we propose the use of ETL patterns to build specific ETL packages. In this paper, we formalize this approach using the BPMN for modeling more conceptual ETL workflows, mapping them to real execution primitives through the use of a domain-specific language that allows for the generation of specific instances that can be executed in an ETL commercial tool.