Query Workload-Aware Index Structures for Range Searches in 1D, 2D, and High-Dimensional Space

Most current database management systems are optimized for single query execution. Yet, often, queries come as part of a query workload. Therefore, there is a need for index structures that can take into consideration existence of multiple queries in a query workload and efficiently produce accurate results for the entire query workload. These index structures should be scalable to handle large amounts of data as well as large query workloads.;The main objective of this dissertation is to create and design scalable index structures that are optimized for range query workloads. Range queries are an important type of queries with wide-ranging applications. There are no existing index structures that are optimized for efficient execution of range query workloads. There are also unique challenges that need to be addressed for range queries in 1D, 2D, and high-dimensional spaces. In this work, I introduce novel cost models, index selection algorithms, and storage mechanisms that can tackle these challenges and efficiently process a given range query workload in 1D, 2D, and high-dimensional spaces. In particular, I introduce the index structures, HCS (for 1D spaces), cSHB (for 2D spaces), and PSLSH (for high-dimensional spaces) that are designed specifically to efficiently handle range query workload and the unique challenges arising from their respective spaces. I experimentally show the effectiveness of the above proposed index structures by comparing with state-of-the-art techniques.