Automatic NoSQL Schema Design: A Workload-Driven Schema Design Approach for NoSQL Wide Column Stores

NoSQL systems are suitable solutions for big data projects and offer a high level of flexibility in design. A good and efficient schema design for NoSQL wide column stores is not only based on the application’s conceptual data model but also on the queries defined in an application’s workload. In these databases, a manual schema design relies on rules of thumb to choose a good schema. Utility these rules without practices is a big challenge in this area. Because these rules are vague and generic, and must be adapted to each application. One of the ways that researchers use to overcome this challenge is presenting automated schema design. The main contribution of this paper is automated schema design for NoSQL wide column stores. This research proposes a workload-driven approach for the mapping from the application conceptual data model to a database schema with a goal of optimizing query performance. This approach uses workload information to achieve a good workload performance, which result in an optimized schema by minimizing the number of requests to the wide column stores. The experimental results show that automated schema generated by the proposed approach leads to a good workload performance.