KVMod - A novel approach to designKey-Value NoSQL databases

Abstract

Abstract The growth of structured, semi-structured, and unstructured data produced by the new applications is a result of the development and expansion of social networks, the Internet of Things, web technology, mobile devices, and other technologies. However, as traditional databases became less suitable to manage rapidly growing data quantity and the variety of data structures, a new class of database management systems named NoSQL is required to satisfy the new requirements. Although NoSQL databases are generally schemaless, significant research has been conducted on NoSQL design. A literature review presented in this paper let us claim the need to create modeling techniques to describe how to structure data in NoSQL databases. Key-value is one of the NoSQL families, which has received too little attention, especially about its design methodology. Most studies have focused on the other families like column-oriented and document-oriented. This paper aims to present a design approach named KVMod (key-value modeling) specific to key-value databases. The purpose is to provide to the scientific community and engineers a methodology for the design of key-value stores using the maximum automation and therefore the minimum human intervention, which equals the minimum of errors. A software tool called KVDesign has been implemented to automate the proposed methodology and thus the most time-consuming database modeling tasks. The complexity is also discussed to assess the efficiency of our proposed algorithms.