Design principles of semantic binary database management systems
Abstract
The Semantic Binary Data Model (SBM) is a viable alternative to the now-dominant relational data model. SBM would be especially advantageous for applications dealing with complex interrelated networks of objects provided that a robust efficient implementation can be achieved. This dissertation presents an implementation design method for SBM, algorithms, and their analytical and empirical evaluation. Our method allows building a robust and flexible database engine with a wider applicability range and improved performance. Extensions to SBM are introduced and an implementation of these extensions is proposed that allows the database engine to efficiently support applications with a predefined set of queries. A New Record data structure is proposed. Trade-offs of employing Fact, Record and Bitmap Data structures for storing information in a semantic database are analyzed. A clustering ID distribution algorithm and an efficient algorithm for object ID encoding are proposed. Mapping to an XML data model is analyzed and a new XML-based XSDL language facilitating interoperability of the system is defined. Solutions to issues associated with making the database engine multi-platform are presented. An improvement to the atomic update algorithm suitable for certain scenarios of database recovery is proposed. Specific guidelines are devised for implementing a robust and well-performing database engine based on the extended Semantic Data Model.
Subject Area
Computer science
Recommended Citation
Vasilevsky, Dmitry, "Design principles of semantic binary database management systems" (2004). ProQuest ETD Collection for FIU. AAI3130422.
https://digitalcommons.fiu.edu/dissertations/AAI3130422