Search

In this paper we propose a new query processing method for the OLAP enabled grid, which blends sophisticated cache extraction techniques and data grid scheduling to efficiently satisfy OLAP queries in a distributed fashion. The heart of our approach is our query fragment aggregation and recombination (FAR) strategy that partitions OLAP queries into subqueries which can be effectively answered by retrieving and aggregating multiple fragments of cached data from nearby grid sources, or as a last resort, more remote backend data warehouses. We have implemented and experimentally evaluated our query processing method and found that our strategy reduces query time between 50% and 60% for practical user cache sizes and network parameters.