Extending an index-benchmarking framework with non-invasive visualization capability

Abstract

Finding a suitable multi-dimensional index structure for a data-intensive system is not a trivial task. The QuEval framework supports users in finding the best index structure from a list of candidates. Nevertheless, if an index structure shows itself superior to other index structures most oft the times, but fails for one data set, we want to know the reason for this phenomenon. To support an understanding of deficits, a visualization of the partitioning scheme is helpful. Consequently, we propose a visualization component which interacts with QuEval without affecting the performance evaluation. Thus, we use a modern software-engineering approach based on AspectJ to support Digital Engineering of complex solutions.