Evolution of Data Warehouses’ Optimization: A Workload Perspective

Abstract

Data warehouse (DW) evolution usually means evolution of its model. However, a decision support system is composed of the DW and of several other components, such as optimization structures like indices or materialized views. Thus, dealing with the DW evolution also implies dealing with the maintenance of these structures. However, propagating evolution to these structures thereby maintaining the coherence with the evolutions on the DW is not always enough. In some cases propagation is not sufficient and redeployment of optimization strategies may be required. Selection of optimization strategies is mainly based on workload, corresponding to user queries. In this paper, we propose to make the workload evolve in response to DW schema evolution. The objective is to avoid waiting for a new workload from the updated DW model. We propose to maintain existing queries coherent and create new queries to deal with probable future analysis needs.