Compression of OLAP Cubes for Aggregate Queries Based on Copula Approach

This paper introduces Copula approach, which has been widely used in statistical field, to the construction of OLAP cubes for the first time. Based on this approach, a novel scheme is proposed to compress data and answer any OLAP query without accessing raw data. The procedure of this scheme can be generally divided into three steps. Firstly, find the proper distribution functions to fit the marginal distribution of each attribute. Secondly, employ Copula approach to catch the intra relationship among attributes in a data set. Finally, use the probability density function of joint distribution to calculate the aggregation function. Empirical evidence shows that this Copula-based model can not only drastically reduce storage requirements but also save the query response time, while the accuracy is bounded under a given level.