Improving Index Selection Accuracy for Star Join Queries Processing: An Association Rules Based Approach

Nowadays, the new technologies for Business Intelligence as DataWarehouse, OLAP, Data Mining, emerged and are needed for the managerial process. In the area of decision support systems, a basic role is held by a data warehouse which is an online repository for decision support applications using complex star join queries. Answering such queries efficiently is often difficult due to the complex nature of both the data and the queries. One of the most challenging tasks for the data warhouse administrator (DWA) is the selection of a set of indexes to attain optimal performance for a given workload under storage constraint. The problem is shown to be NP-hard since it involves searching a vast space of possible configurations. It is very much important to extract meaningful information from the workload which represents the major step towards building relevant indexes. This paper presents an approach for selecting an optimized index configuration using association rules with Apriori algorithm which can drive to understand with more accuracy the attributes correlation. This helps to recommend an index set that closely match the requirements of the provided workload. Experimented using the ABP-1 benchmark, our proposed approach achieves good performance compared with previous studies.