Analysis and Optimization for Boolean Expression Indexing

作者：Sadoghi Mohammad^*; Jacobsen Hans Arno

来源：ACM Transactions on Database Systems, 2013, 38(2): 8.

DOI：10.1145/2487259.2487260

• Algorithms
• Design
• Measurement
• Experimentation
• Performance
• Boolean expressions
• complex event processing
• data structure
• publish/subscribe

BE-Tree is a novel dynamic data structure designed to efficiently index Boolean expressions over a high-dimensional discrete space. BE-Tree copes with both high-dimensionality and expressiveness of Boolean expressions by introducing an effective two-phase space-cutting technique that specifically utilizes the discrete and finite domain properties of the space. Furthermore, BE-Tree employs self-adjustment policies to dynamically adapt the tree as the workload changes. Moreover, in BE-Tree, we develop two novel cache-conscious predicate evaluation techniques, namely, lazy and bitmap evaluations, that also exploit the underlying discrete and finite space to substantially reduce BE-Tree's matching time by up to 75%.
BE-Tree is a general index structure for matching Boolean expression which has a wide range of applications including (complex) event processing, publish/subscribe matching, emerging applications in cospaces, profile matching for targeted web advertising, and approximate string matching. Finally, the superiority of BE-Tree is proven through a comprehensive evaluation with state-of-the-art index structures designed for matching Boolean expressions.

• 出版日期2013-6